# Arihaan Jobs API and MCP server: full docs > Live job postings from employers' own career sites, by MCP (https://jobs-api.arihaan.ai/mcp), REST API (https://jobs-api.arihaan.ai/v1) or files. Pricing: https://jobs.arihaan.ai/pricing (from $35 a month). Index: https://jobs.arihaan.ai/llms.txt # Arihaan Jobs API and MCP server docs Source: https://jobs.arihaan.ai/docs Live job postings from employers’ own career sites, served through a REST API and an MCP server your AI assistant can use directly. Open jobs … Countries … Employers … Updated Daily [ Connect your AI ChatGPT, Claude, Cursor, VS Code and more, step by step. ](https://jobs.arihaan.ai/docs/connect)[ Quickstart Your first search in two minutes with curl, Python or JavaScript. ](https://jobs.arihaan.ai/docs/quickstart)[ MCP server Transport, auth, discovery, and every tool the model sees. ](https://jobs.arihaan.ai/docs/mcp)[ REST API reference Endpoints, parameters, responses and errors. ](https://jobs.arihaan.ai/docs/api)[ Filters 23 filters: title, place, work mode, experience, pay, skills, dates. ](https://jobs.arihaan.ai/docs/filters)[ Company data Size, revenue, funding, founded, and who is hiring. ](https://jobs.arihaan.ai/docs/api/companies) Prefer paying per job to a monthly plan? [Pay per job from $0.016 per 1,000 jobs, start free](https://jobs.mobiusengine.ai/pay-per-job), on jobs.mobiusengine.ai. ## What you get - **Fresh data.** Crawled every night from Workday, Greenhouse, Lever, Ashby, SmartRecruiters and more. Closed jobs are removed the same night. - **Real apply links.** Every job links to the employer’s own application page. - **Structured fields.** Experience, employment type, published pay, skills, work mode, company industry and size. - **Two doors, one account.** The REST API and the MCP server share filters, data and one daily token allowance. ## Getting access Sign in with Google at [the portal](https://jobs.arihaan.ai/login): a new account starts on the free plan (about 10 US jobs a day with the core fields, approximate, no card) and your first API key is created on the spot. For more, pick a plan on the [pricing page](https://jobs.arihaan.ai/pricing) and pay with the same Google account. --- # Quickstart Source: https://jobs.arihaan.ai/docs/quickstart From zero to your first search in two minutes. 1. 1 **Sign in** at [the portal](https://jobs.arihaan.ai/login) with Google. A new account starts on the free plan; your first key is shown once: copy it. 2. 2 **Save the key** in an environment variable: `export MOBIUS_JOBS_KEY=mjd_live_…` 3. 3 **Search.** Run one of the requests below. bash ``` curl -s "https://jobs-api.arihaan.ai/v1/jobs?title=Product%20Manager&countries=US&posted_within_days=7&limit=5" \ -H "Authorization: Bearer $MOBIUS_JOBS_KEY" ``` ## Next steps [ Use it from ChatGPT or Claude No code: connect and ask in plain English. ](https://jobs.arihaan.ai/docs/connect)[ Learn the filters Combine title, place, pay and freshness precisely. ](https://jobs.arihaan.ai/docs/filters)[ Page through results Cursor paging that never skips a job. ](https://jobs.arihaan.ai/docs/paging)[ Try the playground Build a search visually and copy the request. ](https://jobs.arihaan.ai/app/playground) --- # Authentication Source: https://jobs.arihaan.ai/docs/authentication Two ways in: an API key for your code and coding tools, OAuth sign-in for AI apps. ## API keys Send your key on every request, either way: http ``` Authorization: Bearer mjd_live_… # or x-api-key: mjd_live_… ``` - Create and revoke keys on the [API keys](https://jobs.arihaan.ai/app/keys) page. Up to 10 active keys per account. - A key is shown **once**. We store only a hash of it, so a lost key cannot be recovered; make a new one. - Keys start with `mjd_live_` and carry a checksum, so a mistyped key is refused instantly. - A revoked key stops working within a minute on every server. Keep keys server-side Anyone with a key can spend your request limit. Don’t ship it in a browser or mobile app; call the API from your server. ## OAuth (ChatGPT, Claude and other AI apps) AI apps cannot paste a key, so they sign you in instead. You add `https://jobs-api.arihaan.ai/mcp` as a connector, the app opens our sign-in page, you continue with Google and click **Allow**. The app receives a token that works like a key for your account. - OAuth 2.1 with PKCE. Clients register themselves (dynamic client registration) or use a Client ID Metadata Document. - Discovery: `/.well-known/oauth-protected-resource/mcp` and `/.well-known/oauth-authorization-server`. - Access tokens last 1 hour and refresh automatically for 30 days. - See and disconnect connected apps on the [API keys](https://jobs.arihaan.ai/app/keys) page. --- # Limits and usage Source: https://jobs.arihaan.ai/docs/limits Your plan is a number of tokens a day, shared by all your keys and connected apps, counted on the data we send back. | | Your plan | | --- | --- | | Tokens a day | The volume you picked on the [pricing page](https://jobs.arihaan.ai/pricing) (500,000 on the $35 plan, about 250 jobs, approximate); resets 00:00 UTC | | Requests at the same time | 5 | | Jobs per request | up to 100 | | Values per filter | up to 50 (titles, companies, locations…) | | Active API keys | 10 | ## What uses tokens Bigger answers use more: ask for the number of jobs you need. Reading the manual (`/v1/meta`, `/v1/usage`, `/v1/openapi.json`, MCP `describe_catalog`) is free, and a call that returns an error costs nothing. Once your daily tokens are used, calls are refused until the day resets. ## Headers | Header | Meaning | | --- | --- | | `X-RateLimit-Limit` | Your tokens a day | | `X-RateLimit-Remaining` | Tokens left today | | `X-RateLimit-Reset` | When the day resets (Unix seconds) | | `Retry-After` | On a 429: seconds until you can call again | ## Searching descriptions `description` and `exclude_description` need a `title` or `company` in the same search, for example Data Engineer jobs that mention Snowflake. Descriptions are then read only for the jobs those already narrow down, so the search stays fast. To find every job that asks for a tool or skill (Snowflake, Python, dbt) across all companies, use `skills` instead: it covers the whole catalog and answers in seconds. ## How long a request can run A REST call can run for up to 2 minutes and an MCP tool call for up to 80 seconds (ChatGPT and Claude stop waiting at about a minute). Almost every search answers in a few seconds; one that would take longer comes back as `400 too_broad`, asking you to add a title, company or location. ## Going over a limit Up to 5 of your requests can run at the same time. A 6th sent while 5 are still running is refused at once with `429 limit_reached` and `Retry-After: 1`; as soon as one finishes, the next can start. Sending calls one after another, or a few at a time, never hits it. Past your tokens for the day, the error says so and `Retry-After` is the seconds until 00:00 UTC. A refused request costs nothing. Your live usage is on the [dashboard](https://jobs.arihaan.ai/app) and at [GET /v1/usage](https://jobs.arihaan.ai/docs/api/usage). Need more? Pick a bigger plan on the [pricing page](https://jobs.arihaan.ai/pricing) or [contact us](https://jobs.arihaan.ai/support). --- # Connect ChatGPT, Claude and Cursor to job data Source: https://jobs.arihaan.ai/docs/connect Use Arihaan Jobs from ChatGPT, Claude or any AI app. Pick yours below. ## AI apps [ ChatGPT Set up in 2 minutes. ](https://jobs.arihaan.ai/docs/connect/chatgpt)[ Claude Connect in one click. ](https://jobs.arihaan.ai/docs/connect/claude)[ Custom GPT Build your own GPT on our API. ](https://jobs.arihaan.ai/docs/connect/custom-gpt) ## Coding tools [ Claude Code One command in your terminal. ](https://jobs.arihaan.ai/docs/connect/claude-code)[ Cursor Paste one config block. ](https://jobs.arihaan.ai/docs/connect/cursor)[ VS Code Copilot Chat in agent mode. ](https://jobs.arihaan.ai/docs/connect/vscode)[ Codex CLI Two lines of config. ](https://jobs.arihaan.ai/docs/connect/codex)[ Gemini CLI One settings block. ](https://jobs.arihaan.ai/docs/connect/gemini)[ Windsurf One config block. ](https://jobs.arihaan.ai/docs/connect/windsurf)[ Any MCP app Any client that speaks MCP over HTTP. ](https://jobs.arihaan.ai/docs/connect/other) ## APIs and code [ OpenAI API Any OpenAI model, with our tools. ](https://jobs.arihaan.ai/docs/connect/openai-api)[ Anthropic API Claude, with our tools. ](https://jobs.arihaan.ai/docs/connect/anthropic-api)[ Grok (xAI API) Grok, with our tools. ](https://jobs.arihaan.ai/docs/connect/grok)[ REST API Plain HTTPS and JSON. ](https://jobs.arihaan.ai/docs/connect/rest) ## Custom setup Arihaan Jobs is a remote MCP server. Point any MCP client at this URL. Chat apps sign in with Google; everything else uses an API key from the [API keys page](https://jobs.arihaan.ai/app/keys). MCP server URL url ``` https://jobs-api.arihaan.ai/mcp ``` First prompt to try “What filters does Arihaan Jobs support?” The model calls `describe_catalog` and learns every filter and value by itself. --- # Connect ChatGPT to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/chatgpt Connect your AI · Google sign-in # ChatGPT Set up in 2 minutes. 1. 1 Open [ChatGPT](https://chatgpt.com) on the web and go to Settings → Security and login. Turn on Developer mode. 2. 2 Open Plugins in the sidebar and click +. 3. 3 Name it Arihaan Jobs and paste this as the MCP server URL: `https://jobs-api.arihaan.ai/mcp` 4. 4 Choose OAuth for authentication and click Create. 5. 5 Sign in with your invited Google account and click Allow. 6. 6 Start a new chat, click + → Developer mode → Arihaan Jobs. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Claude to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/claude Connect your AI · Google sign-in # Claude Connect in one click. 1. 1 Open Arihaan Jobs in Claude's directory and click Connect. [Connect in Claude](https://claude.ai/directory/arihaan-jobs) 2. 2 Sign in with your invited Google account and click Allow. 3. 3 Ask Claude about any job. If it doesn't use Arihaan Jobs, click + → Connectors and switch it on. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Claude Code to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/claude-code Connect your AI · API key # Claude Code One command in your terminal. 1. 1 Run this in a terminal. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). bash ``` claude mcp add --transport http arihaan-jobs https://jobs-api.arihaan.ai/mcp \ --header "Authorization: Bearer YOUR_API_KEY" ``` 2. 2 Start claude and ask your question. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Cursor to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/cursor Connect your AI · API key # Cursor Paste one config block. 1. 1 Open Cursor Settings → MCP → Add new global MCP server. 2. 2 Paste this and save. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). ~/.cursor/mcp.json json ``` { "mcpServers": { "arihaan-jobs": { "url": "https://jobs-api.arihaan.ai/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } } ``` 3. 3 Check that arihaan-jobs shows a green dot, then ask in the chat. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect VS Code to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/vscode Connect your AI · API key # VS Code Copilot Chat in agent mode. 1. 1 Create this file in your project. .vscode/mcp.json json ``` { "inputs": [ { "type": "promptString", "id": "arihaan-jobs-key", "description": "Arihaan API key", "password": true } ], "servers": { "arihaan-jobs": { "type": "http", "url": "https://jobs-api.arihaan.ai/mcp", "headers": { "Authorization": "Bearer ${input:arihaan-jobs-key}" } } } } ``` 2. 2 Click Start above the server in that file and paste your key from the [API keys page](https://jobs.arihaan.ai/app/keys) when asked. 3. 3 Open Copilot Chat, switch to Agent mode and ask. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Codex CLI to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/codex Connect your AI · API key # Codex CLI Two lines of config. 1. 1 Add this to your Codex config. ~/.codex/config.toml toml ``` [mcp_servers.arihaan-jobs] url = "https://jobs-api.arihaan.ai/mcp" bearer_token_env_var = "MOBIUS_JOBS_KEY" ``` 2. 2 Save your key in the environment. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). bash ``` export MOBIUS_JOBS_KEY=YOUR_API_KEY ``` 3. 3 Run codex and ask. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Gemini CLI to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/gemini Connect your AI · API key # Gemini CLI One settings block. 1. 1 Add this to your Gemini settings. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). ~/.gemini/settings.json json ``` { "mcpServers": { "arihaan-jobs": { "httpUrl": "https://jobs-api.arihaan.ai/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } } ``` 2. 2 Run gemini, type /mcp to check it is connected, then ask. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Windsurf to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/windsurf Connect your AI · API key # Windsurf One config block. 1. 1 Open Windsurf Settings → Cascade → MCP servers → View raw config. 2. 2 Paste this and save. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). ~/.codeium/windsurf/mcp\_config.json json ``` { "mcpServers": { "arihaan-jobs": { "serverUrl": "https://jobs-api.arihaan.ai/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } } ``` 3. 3 Click refresh, then ask Cascade. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect OpenAI API to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/openai-api Connect your AI · API key # OpenAI API Any OpenAI model, with our tools. 1. 1 Install the SDK and set your [OpenAI key](https://platform.openai.com/api-keys). bash ``` pip install openai export OPENAI_API_KEY=sk-… ``` 2. 2 Run this. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). python ``` from openai import OpenAI client = OpenAI() resp = client.responses.create( model="gpt-5", tools=[{ "type": "mcp", "server_label": "mobius_jobs", "server_url": "https://jobs-api.arihaan.ai/mcp", "headers": {"Authorization": "Bearer YOUR_API_KEY"}, "require_approval": "never", }], input="Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.", ) print(resp.output_text) ``` Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Anthropic API to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/anthropic-api Connect your AI · API key # Anthropic API Claude, with our tools. 1. 1 Install the SDK and set your [Anthropic key](https://console.anthropic.com/settings/keys). bash ``` pip install anthropic export ANTHROPIC_API_KEY=sk-ant-… ``` 2. 2 Run this. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). python ``` import anthropic client = anthropic.Anthropic() msg = client.beta.messages.create( model="claude-sonnet-5", max_tokens=2000, betas=["mcp-client-2025-11-20"], mcp_servers=[{ "type": "url", "url": "https://jobs-api.arihaan.ai/mcp", "name": "arihaan-jobs", "authorization_token": "YOUR_API_KEY", }], tools=[{"type": "mcp_toolset", "mcp_server_name": "arihaan-jobs"}], messages=[{"role": "user", "content": "Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link."}], ) print(msg.content[-1].text) ``` Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Grok (xAI API) to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/grok Connect your AI · API key # Grok (xAI API) Grok, with our tools. 1. 1 Install the SDK and set your [xAI key](https://console.x.ai). bash ``` pip install openai export XAI_API_KEY=xai-… ``` 2. 2 Run this. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). python ``` import os from openai import OpenAI client = OpenAI(api_key=os.environ["XAI_API_KEY"], base_url="https://api.x.ai/v1") resp = client.responses.create( model="grok-4.7", tools=[{ "type": "mcp", "server_url": "https://jobs-api.arihaan.ai/mcp", "server_label": "arihaan-jobs", "authorization": "Bearer YOUR_API_KEY", }], input="Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.", ) print(resp.output_text) ``` Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Custom GPT to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/custom-gpt Connect your AI · API key # Custom GPT Build your own GPT on our API. 1. 1 Open the [GPT editor](https://chatgpt.com/gpts/editor) in ChatGPT, then Configure → Create new action. 2. 2 Click Import from URL and paste: `https://jobs-api.arihaan.ai/v1/openapi.json` 3. 3 Under Authentication choose API Key, auth type Bearer, and paste your key from the [API keys page](https://jobs.arihaan.ai/app/keys). Save. Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Job postings REST API setup Source: https://jobs.arihaan.ai/docs/connect/rest Connect your AI · API key # REST API Plain HTTPS and JSON. 1. 1 Run this. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). bash ``` curl -s "https://jobs-api.arihaan.ai/v1/jobs?title=Data%20Engineer&countries=US&work_mode=Remote%20Solely&posted_within_days=7&limit=5" \ -H "Authorization: Bearer YOUR_API_KEY" ``` Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Connect Any MCP app to live job data with MCP Source: https://jobs.arihaan.ai/docs/connect/other Connect your AI · API key # Any MCP app Any client that speaks MCP over HTTP. 1. 1 Add a remote (Streamable HTTP) MCP server with this URL: `https://jobs-api.arihaan.ai/mcp` 2. 2 Add this header. Replace YOUR\_API\_KEY with your key from the [API keys page](https://jobs.arihaan.ai/app/keys). `Authorization: Bearer YOUR_API_KEY` Try this prompt “Use Arihaan Jobs to find remote data engineer jobs posted in the last 7 days that list pay. Show the title, company, pay and apply link.” --- # Job search MCP server: overview Source: https://jobs.arihaan.ai/docs/mcp A remote Model Context Protocol server over Streamable HTTP. Stateless, read-only, and the same data as the REST API. | | | | --- | --- | | URL | `https://jobs-api.arihaan.ai/mcp` | | Transport | Streamable HTTP (JSON responses); stateless, any instance can answer | | Auth | OAuth 2.1 (AI apps) or `Authorization: Bearer ` | | Protected resource metadata | `https://jobs-api.arihaan.ai/.well-known/oauth-protected-resource/mcp` | | Authorization server metadata | `https://jobs-api.arihaan.ai/.well-known/oauth-authorization-server` | | Tools | [10 tools](https://jobs.arihaan.ai/docs/mcp/tools), all marked read-only | ## Raw JSON-RPC Most people never see this layer, but it helps when debugging: bash ``` curl -s https://jobs-api.arihaan.ai/mcp \ -H "Authorization: Bearer $MOBIUS_JOBS_KEY" \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"count_jobs","arguments":{"title":["Data Engineer"],"countries":["US"]}}}' ``` ## Inspect it bash ``` npx @modelcontextprotocol/inspector # Transport: Streamable HTTP · URL: https://jobs-api.arihaan.ai/mcp # Header: Authorization: Bearer YOUR_API_KEY ``` Every tool that reads jobs counts as one request, `catalog_stats` included. `describe_catalog` is free, so a model can read the manual as often as it likes. --- # MCP tools: search_jobs, count_jobs, get_company Source: https://jobs.arihaan.ai/docs/mcp/tools What the model sees. Descriptions are written for the model, so they say exactly what each filter does. ## describe\_catalog Every filter with its type and allowed values, live facts about the data (counts, freshness, sources, countries, industries, field coverage) and the caller’s usage. **Free.** Models should call it first. ## search\_jobs Search open jobs, newest first. Filters combine with AND. Returns `{jobs, count, next_cursor}`. Arguments (all optional) `title`string\[\] Title has ANY of these as words, case and punctuation ignored; the last word may continue ('Product Lead' finds 'Product Leader'). `title_exclude`string\[\] Drop jobs whose title contains ANY of these. `title_whole_words`boolean Match title and title\_exclude as whole words only: the last word is not continued ('Lead' does not find 'Leader'). Words are always whole: 'CTO' never finds 'Director', excluding 'IT' keeps 'Security Analyst'. `company`string\[\] Only these companies (substring of the company name or its board key). `exclude_company`string\[\] Drop these companies (substring match). `sources`string\[\] Only jobs from these applicant-tracking systems, or whose apply link is on one (an employer's career site whose Apply goes to its Workday board matches 'workday'). `workday``greenhouse``lever``ashby``smartrecruiters``oraclecloud``successfactors``icims``workable``bamboohr``teamtailor``paylocity``adp``paycom``ukg``jazzhr``dayforce``recruitee``breezy``personio``jobvite``pinpoint``rippling``applicantpro``peopleadmin``isolvedhire``usajobs``gem``governmentjobs``schooljobs``taleo``manatal``jsonld_sitemap``zohorecruit``comeet``jobscore``ycombinator` `exclude_sources`string\[\] Drop jobs from these applicant-tracking systems, or whose apply link is on one, e.g. \['manatal'\] (its boards are mostly recruiting agencies). `industry`string\[\] Company industry contains ANY (LinkedIn industry names). `exclude_industry`string\[\] Drop companies whose industry contains ANY of these. Jobs whose industry is unknown are kept. `skills`string\[\] The job lists ANY of these skills (whole skill, case-insensitive). `company_size`string\[\] Company headcount bucket(s). Unknown size is excluded. `1``2-10``11-50``51-200``201-500``501-1000``1001-5000``5001-10000``10000+` `exclude_agencies`boolean Drop staffing and recruiting agencies. `sector`string\[\] Company sector(s), from our company profile (98.7% of jobs). `AGRICULTURE``CONSTRUCTION_AND_REAL_ESTATE``CONSUMER_GOODS``EDUCATION``ENERGY``FINANCIAL_SERVICES``GOVERNMENT``HARDWARE_AND_ELECTRONICS``HEALTHCARE``HOSPITALITY``INSURANCE``MANUFACTURING``MEDIA_AND_ENTERTAINMENT``NONPROFIT``OTHER``PHARMA_AND_BIOTECH``PROFESSIONAL_SERVICES``RETAIL``SOFTWARE``STAFFING``TELECOMMUNICATIONS``TRANSPORTATION_AND_LOGISTICS` `company_kind`string\[\] Kind of employer: OPERATING\_COMPANY, CONSULTING, STAFFING\_AGENCY … `CONSULTING``EDUCATION``GOVERNMENT``HEALTH_PROVIDER``NONPROFIT``OPERATING_COMPANY``STAFFING_AGENCY` `customer`string\[\] Who the company sells to. `B2B``B2C``B2G``BOTH` `ownership`string\[\] PUBLIC, PRIVATE, NONPROFIT … Companies with unknown ownership are excluded. `EDUCATION``GOVERNMENT``NONPROFIT``PRIVATE``PUBLIC` `work_mode`string\[\] ANY of: On-site (the posting never mentions remote, hybrid or work from home, or its text says the job is on site), Remote OK (it mentions remote anywhere and its text does not say the job is hybrid or on site), Remote Solely (title or location says remote, same exception), Hybrid (title or location says hybrid, or its text does). All four = no filter. `On-site``Hybrid``Remote OK``Remote Solely` `exclude_work_mode`string\[\] Drop jobs matching ANY of these work modes (same rules as work\_mode). \['Remote Solely'\] keeps every job someone could go in to. `On-site``Hybrid``Remote OK``Remote Solely` `description`string\[\] The title or full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `exclude_description`string\[\] Drop jobs whose full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `taxonomies`string\[\] Job category, Fantastic's names. Read from the job's function flags, the company's sector or kind, and title words; any one is enough. `Technology``Healthcare``Management & Leadership``Finance & Accounting``Human Resources``Sales``Marketing``Customer Service & Support``Education``Legal``Engineering``Science & Research``Trades``Construction``Manufacturing``Logistics``Creative & Media``Hospitality``Retail``Data & Analytics``Software``Energy``Agriculture``Government & Public Sector``Art & Design``Transportation``Consulting` `education`string\[\] The job's requirements ask for ANY of these. `high school``associate degree``bachelor degree``professional certificate``postgraduate degree` `visa`string only = the job offers visa sponsorship (the company sponsors, or the posting says so, and the posting never refuses); exclude = it does not. `only``exclude` `remote_friendly`boolean true = the posting mentions remote/hybrid/WFH anywhere; false = it does not. Prefer work\_mode. `countries`string\[\] ISO-3166 alpha-2 country codes. `locations`string\[\] ANY of these places. Each is 'City, State', 'State' or 'City'; every comma part must match. US states in full or as postal codes. `exclude_locations`string\[\] Drop jobs in ANY of these places (same rules as locations). `experience`string\[\] Years of experience asked for. Postings that do not say are kept. `0-2``2-5``5-10``10+` `employment_type`string\[\] Employment type. Postings that do not say are kept. `FULL_TIME``PART_TIME``CONTRACTOR``TEMPORARY``INTERN` `min_salary_annual`number Published annual pay at least this much. Postings that publish no pay are kept; add has\_salary=true to drop them. Estimates never count. `has_salary`boolean Only jobs whose posting states pay. `posted_within_days`integer 1-365 Posted (or first seen) in the last N days, today included. `posted_since`date (YYYY-MM-DD) Posted (or first seen) on or after this date, YYYY-MM-DD. `posted_before`date (YYYY-MM-DD) Posted (or first seen) before this date, YYYY-MM-DD. `include_internships`boolean Internships and co-ops are included by default; false leaves them out. `limit`integer Jobs per page. `cursor`string next\_cursor from the previous page. The way to page. `offset`integer Skip N jobs (max 5,000). Use cursor for deeper paging. `include_description`boolean Include each job's full description, requirements, responsibilities, job function and AI flags (large). `include_company`boolean Attach each job's full company profile (size, headcount, revenue range, funding, founded, headquarters, followers). ## count\_jobs How many jobs match. Same filter arguments as `search_jobs`, without paging. Add `group_by` (company, country, state, city, source, experience, employment\_type or industry) for the biggest groups, `top` (1-50) at a time; pass the answer's `next_group_offset` as `group_offset` for the next ones (companies 51-100, and so on). `include_pay_stats` adds published-pay figures; over very broad searches it can be too slow, so add a title or place. ## get\_job Arguments `job_id`stringrequired The id from search\_jobs. One job in full, including the description. ## get\_jobs Arguments `job_ids`string\[\] (max 100)required Ids from search\_jobs. Several jobs in full, in the order given. Ids that no longer exist come back in `missing`. ## search and fetch The two tools ChatGPT deep research and company knowledge call, in OpenAI’s exact shape: `search(query)` returns `{results: [{id, title, url}]}` from a free-text query; `fetch(id)` returns `{id, title, text, url, metadata}` with the full posting as text. ## get\_company Arguments `company`stringrequired A name (Stripe) or LinkedIn slug (stripe). The company profile (industry, size, headcount, revenue range, funding, founded, headquarters, followers) and its live hiring: open jobs, top locations and titles. ## find\_companies Companies by `name`, `industry` or `company_size`, each with its open-job count. ## catalog\_stats Totals and date range of the index. Free. --- # Prompting tips Source: https://jobs.arihaan.ai/docs/mcp/prompting Small wording changes get much better searches from an assistant. - **Name the tool once.** “Use Arihaan Jobs to…” makes the assistant reach for it instead of the web. - **Give several title phrasings.** “data engineer or analytics engineer or ETL developer” becomes three title keywords. - **Say how fresh.** “posted this week” maps to `posted_within_days=7`. - **Say if pay must be listed.** Salary floors keep jobs that don’t publish pay unless you ask for listed pay only. - **Be explicit about remote.** “fully remote” maps to work mode Remote Solely; “remote friendly” is broader. - **Ask for counts first** for big questions: “how many…” is one cheap call before paging through results. ## Example prompts text ``` Use Arihaan Jobs to find fully remote senior data or analytics engineer jobs in the US, posted in the last 7 days, that list pay of at least $150k. Show title, company, pay and the apply link. ``` text ``` How many nursing jobs are open in Texas right now? Break it down by city for the top 5 cities. ``` --- # Job postings API reference Source: https://jobs.arihaan.ai/docs/api JSON over HTTPS. Every endpoint below takes an API key. | | | | --- | --- | | Base URL | `https://jobs-api.arihaan.ai/v1` | | Format | JSON responses, UTF-8 | | Auth | [Bearer API key](https://jobs.arihaan.ai/docs/authentication) | | Spec | [OpenAPI 3.1](https://jobs.arihaan.ai/v1/openapi.json) | ## Endpoints | Method | Path | What | | --- | --- | --- | | GET | [`/v1/jobs`](https://jobs.arihaan.ai/docs/api/search) | Search jobs (query parameters) | | POST | [`/v1/jobs/search`](https://jobs.arihaan.ai/docs/api/search-post) | Search jobs (JSON body) | | GET / POST | [`/v1/jobs/count`](https://jobs.arihaan.ai/docs/api/count) | Count matching jobs | | GET | [`/v1/jobs/{id}`](https://jobs.arihaan.ai/docs/api/get-job) | One job with its description | | POST | [`/v1/jobs/batch`](https://jobs.arihaan.ai/docs/api/batch) | Up to 100 jobs by id | | GET | [`/v1/companies`](https://jobs.arihaan.ai/docs/api/companies) | Find companies | | GET | [`/v1/companies/{name}`](https://jobs.arihaan.ai/docs/api/companies) | A company profile and its hiring | | GET | [`/v1/meta`](https://jobs.arihaan.ai/docs/api/meta) | Filters and data facts (free) | | GET | [`/v1/usage`](https://jobs.arihaan.ai/docs/api/usage) | Your usage (free) | ## Conventions - List filters take several values: repeat the parameter (`?title=Nurse&title=RN`). Fixed-value lists may also be comma-separated (`?countries=US,CA`). - Unknown parameters are an error, not ignored, so a typo never silently matches everything. - Results are newest first. Page with [cursors](https://jobs.arihaan.ai/docs/paging). --- # Search jobs: job postings API Source: https://jobs.arihaan.ai/docs/api/search Search open jobs, newest first. Every filter is a query parameter. GET`/v1/jobs` Query parameters (all optional) `title`string\[\] Title has ANY of these as words, case and punctuation ignored; the last word may continue ('Product Lead' finds 'Product Leader'). `title_exclude`string\[\] Drop jobs whose title contains ANY of these. `title_whole_words`boolean Match title and title\_exclude as whole words only: the last word is not continued ('Lead' does not find 'Leader'). Words are always whole: 'CTO' never finds 'Director', excluding 'IT' keeps 'Security Analyst'. `company`string\[\] Only these companies (substring of the company name or its board key). `exclude_company`string\[\] Drop these companies (substring match). `sources`string\[\] Only jobs from these applicant-tracking systems, or whose apply link is on one (an employer's career site whose Apply goes to its Workday board matches 'workday'). `workday``greenhouse``lever``ashby``smartrecruiters``oraclecloud``successfactors``icims``workable``bamboohr``teamtailor``paylocity``adp``paycom``ukg``jazzhr``dayforce``recruitee``breezy``personio``jobvite``pinpoint``rippling``applicantpro``peopleadmin``isolvedhire``usajobs``gem``governmentjobs``schooljobs``taleo``manatal``jsonld_sitemap``zohorecruit``comeet``jobscore``ycombinator` `exclude_sources`string\[\] Drop jobs from these applicant-tracking systems, or whose apply link is on one, e.g. \['manatal'\] (its boards are mostly recruiting agencies). `industry`string\[\] Company industry contains ANY (LinkedIn industry names). `exclude_industry`string\[\] Drop companies whose industry contains ANY of these. Jobs whose industry is unknown are kept. `skills`string\[\] The job lists ANY of these skills (whole skill, case-insensitive). `company_size`string\[\] Company headcount bucket(s). Unknown size is excluded. `1``2-10``11-50``51-200``201-500``501-1000``1001-5000``5001-10000``10000+` `exclude_agencies`boolean Drop staffing and recruiting agencies. `sector`string\[\] Company sector(s), from our company profile (98.7% of jobs). `AGRICULTURE``CONSTRUCTION_AND_REAL_ESTATE``CONSUMER_GOODS``EDUCATION``ENERGY``FINANCIAL_SERVICES``GOVERNMENT``HARDWARE_AND_ELECTRONICS``HEALTHCARE``HOSPITALITY``INSURANCE``MANUFACTURING``MEDIA_AND_ENTERTAINMENT``NONPROFIT``OTHER``PHARMA_AND_BIOTECH``PROFESSIONAL_SERVICES``RETAIL``SOFTWARE``STAFFING``TELECOMMUNICATIONS``TRANSPORTATION_AND_LOGISTICS` `company_kind`string\[\] Kind of employer: OPERATING\_COMPANY, CONSULTING, STAFFING\_AGENCY … `CONSULTING``EDUCATION``GOVERNMENT``HEALTH_PROVIDER``NONPROFIT``OPERATING_COMPANY``STAFFING_AGENCY` `customer`string\[\] Who the company sells to. `B2B``B2C``B2G``BOTH` `ownership`string\[\] PUBLIC, PRIVATE, NONPROFIT … Companies with unknown ownership are excluded. `EDUCATION``GOVERNMENT``NONPROFIT``PRIVATE``PUBLIC` `work_mode`string\[\] ANY of: On-site (the posting never mentions remote, hybrid or work from home, or its text says the job is on site), Remote OK (it mentions remote anywhere and its text does not say the job is hybrid or on site), Remote Solely (title or location says remote, same exception), Hybrid (title or location says hybrid, or its text does). All four = no filter. `On-site``Hybrid``Remote OK``Remote Solely` `exclude_work_mode`string\[\] Drop jobs matching ANY of these work modes (same rules as work\_mode). \['Remote Solely'\] keeps every job someone could go in to. `On-site``Hybrid``Remote OK``Remote Solely` `description`string\[\] The title or full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `exclude_description`string\[\] Drop jobs whose full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `taxonomies`string\[\] Job category, Fantastic's names. Read from the job's function flags, the company's sector or kind, and title words; any one is enough. `Technology``Healthcare``Management & Leadership``Finance & Accounting``Human Resources``Sales``Marketing``Customer Service & Support``Education``Legal``Engineering``Science & Research``Trades``Construction``Manufacturing``Logistics``Creative & Media``Hospitality``Retail``Data & Analytics``Software``Energy``Agriculture``Government & Public Sector``Art & Design``Transportation``Consulting` `education`string\[\] The job's requirements ask for ANY of these. `high school``associate degree``bachelor degree``professional certificate``postgraduate degree` `visa`string only = the job offers visa sponsorship (the company sponsors, or the posting says so, and the posting never refuses); exclude = it does not. `only``exclude` `remote_friendly`boolean true = the posting mentions remote/hybrid/WFH anywhere; false = it does not. Prefer work\_mode. `countries`string\[\] ISO-3166 alpha-2 country codes. `locations`string\[\] ANY of these places. Each is 'City, State', 'State' or 'City'; every comma part must match. US states in full or as postal codes. `exclude_locations`string\[\] Drop jobs in ANY of these places (same rules as locations). `experience`string\[\] Years of experience asked for. Postings that do not say are kept. `0-2``2-5``5-10``10+` `employment_type`string\[\] Employment type. Postings that do not say are kept. `FULL_TIME``PART_TIME``CONTRACTOR``TEMPORARY``INTERN` `min_salary_annual`number Published annual pay at least this much. Postings that publish no pay are kept; add has\_salary=true to drop them. Estimates never count. `has_salary`boolean Only jobs whose posting states pay. `posted_within_days`integer 1-365 Posted (or first seen) in the last N days, today included. `posted_since`date (YYYY-MM-DD) Posted (or first seen) on or after this date, YYYY-MM-DD. `posted_before`date (YYYY-MM-DD) Posted (or first seen) before this date, YYYY-MM-DD. `include_internships`boolean Internships and co-ops are included by default; false leaves them out. `limit`integer Jobs per page. `cursor`string next\_cursor from the previous page. The way to page. `offset`integer Skip N jobs (max 5,000). Use cursor for deeper paging. `include_description`boolean Include each job's full description, requirements, responsibilities, job function and AI flags (large). `include_company`boolean Attach each job's full company profile (size, headcount, revenue range, funding, founded, headquarters, followers). bash ``` curl -s "https://jobs-api.arihaan.ai/v1/jobs?title=Data%20Engineer&countries=US&experience=5-10,10%2B&posted_within_days=7&limit=20" \ -H "Authorization: Bearer $MOBIUS_JOBS_KEY" ``` Example response json ``` { "jobs": [ { "id": "greenhouse:acmecloud:7234001", "title": "Senior Data Engineer", "organization": "Acme Cloud", "organization_url": "https://acme.example", "organization_logo": "https://…/logo.png", "org_linkedin_industry": "Software Development", "org_linkedin_size": "1001-5000", "url": "https://boards.greenhouse.io/acmecloud/jobs/7234001", "apply_url": "https://boards.greenhouse.io/acmecloud/jobs/7234001", "source": "greenhouse", "date_posted": "2026-09-26", "date_first_seen": "2026-09-27", "locations_derived": ["Remote, United States"], "countries_derived": ["US"], "remote_friendly": true, "ai_experience_level": "5-10", "ai_employment_type": ["FULL_TIME"], "has_salary": true, "ai_salary_min_value": 170000, "ai_salary_max_value": 210000, "ai_salary_currency": "USD", "ai_salary_unit_text": "YEAR", "ai_key_skills": ["Python", "SQL", "Spark", "Airflow"] } ], "count": 20, "next_cursor": "MjAyNi0wOS0yNnxncmVlbmhvdXNlOmFjbWVjbG91ZDo3MjM0MDAx" } ``` --- # Search jobs (JSON): job postings API Source: https://jobs.arihaan.ai/docs/api/search-post The same search as GET /v1/jobs, with filters in a JSON body. Easier for long title lists and places with commas. POST`/v1/jobs/search` Body fields (all optional) `title`string\[\] Title has ANY of these as words, case and punctuation ignored; the last word may continue ('Product Lead' finds 'Product Leader'). `title_exclude`string\[\] Drop jobs whose title contains ANY of these. `title_whole_words`boolean Match title and title\_exclude as whole words only: the last word is not continued ('Lead' does not find 'Leader'). Words are always whole: 'CTO' never finds 'Director', excluding 'IT' keeps 'Security Analyst'. `company`string\[\] Only these companies (substring of the company name or its board key). `exclude_company`string\[\] Drop these companies (substring match). `sources`string\[\] Only jobs from these applicant-tracking systems, or whose apply link is on one (an employer's career site whose Apply goes to its Workday board matches 'workday'). `workday``greenhouse``lever``ashby``smartrecruiters``oraclecloud``successfactors``icims``workable``bamboohr``teamtailor``paylocity``adp``paycom``ukg``jazzhr``dayforce``recruitee``breezy``personio``jobvite``pinpoint``rippling``applicantpro``peopleadmin``isolvedhire``usajobs``gem``governmentjobs``schooljobs``taleo``manatal``jsonld_sitemap``zohorecruit``comeet``jobscore``ycombinator` `exclude_sources`string\[\] Drop jobs from these applicant-tracking systems, or whose apply link is on one, e.g. \['manatal'\] (its boards are mostly recruiting agencies). `industry`string\[\] Company industry contains ANY (LinkedIn industry names). `exclude_industry`string\[\] Drop companies whose industry contains ANY of these. Jobs whose industry is unknown are kept. `skills`string\[\] The job lists ANY of these skills (whole skill, case-insensitive). `company_size`string\[\] Company headcount bucket(s). Unknown size is excluded. `1``2-10``11-50``51-200``201-500``501-1000``1001-5000``5001-10000``10000+` `exclude_agencies`boolean Drop staffing and recruiting agencies. `sector`string\[\] Company sector(s), from our company profile (98.7% of jobs). `AGRICULTURE``CONSTRUCTION_AND_REAL_ESTATE``CONSUMER_GOODS``EDUCATION``ENERGY``FINANCIAL_SERVICES``GOVERNMENT``HARDWARE_AND_ELECTRONICS``HEALTHCARE``HOSPITALITY``INSURANCE``MANUFACTURING``MEDIA_AND_ENTERTAINMENT``NONPROFIT``OTHER``PHARMA_AND_BIOTECH``PROFESSIONAL_SERVICES``RETAIL``SOFTWARE``STAFFING``TELECOMMUNICATIONS``TRANSPORTATION_AND_LOGISTICS` `company_kind`string\[\] Kind of employer: OPERATING\_COMPANY, CONSULTING, STAFFING\_AGENCY … `CONSULTING``EDUCATION``GOVERNMENT``HEALTH_PROVIDER``NONPROFIT``OPERATING_COMPANY``STAFFING_AGENCY` `customer`string\[\] Who the company sells to. `B2B``B2C``B2G``BOTH` `ownership`string\[\] PUBLIC, PRIVATE, NONPROFIT … Companies with unknown ownership are excluded. `EDUCATION``GOVERNMENT``NONPROFIT``PRIVATE``PUBLIC` `work_mode`string\[\] ANY of: On-site (the posting never mentions remote, hybrid or work from home, or its text says the job is on site), Remote OK (it mentions remote anywhere and its text does not say the job is hybrid or on site), Remote Solely (title or location says remote, same exception), Hybrid (title or location says hybrid, or its text does). All four = no filter. `On-site``Hybrid``Remote OK``Remote Solely` `exclude_work_mode`string\[\] Drop jobs matching ANY of these work modes (same rules as work\_mode). \['Remote Solely'\] keeps every job someone could go in to. `On-site``Hybrid``Remote OK``Remote Solely` `description`string\[\] The title or full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `exclude_description`string\[\] Drop jobs whose full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `taxonomies`string\[\] Job category, Fantastic's names. Read from the job's function flags, the company's sector or kind, and title words; any one is enough. `Technology``Healthcare``Management & Leadership``Finance & Accounting``Human Resources``Sales``Marketing``Customer Service & Support``Education``Legal``Engineering``Science & Research``Trades``Construction``Manufacturing``Logistics``Creative & Media``Hospitality``Retail``Data & Analytics``Software``Energy``Agriculture``Government & Public Sector``Art & Design``Transportation``Consulting` `education`string\[\] The job's requirements ask for ANY of these. `high school``associate degree``bachelor degree``professional certificate``postgraduate degree` `visa`string only = the job offers visa sponsorship (the company sponsors, or the posting says so, and the posting never refuses); exclude = it does not. `only``exclude` `remote_friendly`boolean true = the posting mentions remote/hybrid/WFH anywhere; false = it does not. Prefer work\_mode. `countries`string\[\] ISO-3166 alpha-2 country codes. `locations`string\[\] ANY of these places. Each is 'City, State', 'State' or 'City'; every comma part must match. US states in full or as postal codes. `exclude_locations`string\[\] Drop jobs in ANY of these places (same rules as locations). `experience`string\[\] Years of experience asked for. Postings that do not say are kept. `0-2``2-5``5-10``10+` `employment_type`string\[\] Employment type. Postings that do not say are kept. `FULL_TIME``PART_TIME``CONTRACTOR``TEMPORARY``INTERN` `min_salary_annual`number Published annual pay at least this much. Postings that publish no pay are kept; add has\_salary=true to drop them. Estimates never count. `has_salary`boolean Only jobs whose posting states pay. `posted_within_days`integer 1-365 Posted (or first seen) in the last N days, today included. `posted_since`date (YYYY-MM-DD) Posted (or first seen) on or after this date, YYYY-MM-DD. `posted_before`date (YYYY-MM-DD) Posted (or first seen) before this date, YYYY-MM-DD. `include_internships`boolean Internships and co-ops are included by default; false leaves them out. `limit`integer Jobs per page. `cursor`string next\_cursor from the previous page. The way to page. `offset`integer Skip N jobs (max 5,000). Use cursor for deeper paging. `include_description`boolean Include each job's full description, requirements, responsibilities, job function and AI flags (large). `include_company`boolean Attach each job's full company profile (size, headcount, revenue range, funding, founded, headquarters, followers). bash ``` curl -s -X POST https://jobs-api.arihaan.ai/v1/jobs/search \ -H "Authorization: Bearer $MOBIUS_JOBS_KEY" -H "Content-Type: application/json" \ -d '{"title": ["Data Engineer", "Analytics Engineer"], "locations": ["Chicago, Illinois"], "work_mode": ["Hybrid", "Remote OK"], "has_salary": true, "limit": 20}' ``` Example response json ``` { "jobs": [ { "id": "greenhouse:acmecloud:7234001", "title": "Senior Data Engineer", "organization": "Acme Cloud", "organization_url": "https://acme.example", "organization_logo": "https://…/logo.png", "org_linkedin_industry": "Software Development", "org_linkedin_size": "1001-5000", "url": "https://boards.greenhouse.io/acmecloud/jobs/7234001", "apply_url": "https://boards.greenhouse.io/acmecloud/jobs/7234001", "source": "greenhouse", "date_posted": "2026-09-26", "date_first_seen": "2026-09-27", "locations_derived": ["Remote, United States"], "countries_derived": ["US"], "remote_friendly": true, "ai_experience_level": "5-10", "ai_employment_type": ["FULL_TIME"], "has_salary": true, "ai_salary_min_value": 170000, "ai_salary_max_value": 210000, "ai_salary_currency": "USD", "ai_salary_unit_text": "YEAR", "ai_key_skills": ["Python", "SQL", "Spark", "Airflow"] } ], "count": 20, "next_cursor": "MjAyNi0wOS0yNnxncmVlbmhvdXNlOmFjbWVjbG91ZDo3MjM0MDAx" } ``` --- # Count jobs: job postings API Source: https://jobs.arihaan.ai/docs/api/count How many jobs match. Takes every search filter, no paging. Cheap: use it to size a search before paging. GET`/v1/jobs/count` POST`/v1/jobs/count` Parameters `title`string\[\] Title has ANY of these as words, case and punctuation ignored; the last word may continue ('Product Lead' finds 'Product Leader'). `title_exclude`string\[\] Drop jobs whose title contains ANY of these. `title_whole_words`boolean Match title and title\_exclude as whole words only: the last word is not continued ('Lead' does not find 'Leader'). Words are always whole: 'CTO' never finds 'Director', excluding 'IT' keeps 'Security Analyst'. `company`string\[\] Only these companies (substring of the company name or its board key). `exclude_company`string\[\] Drop these companies (substring match). `sources`string\[\] Only jobs from these applicant-tracking systems, or whose apply link is on one (an employer's career site whose Apply goes to its Workday board matches 'workday'). `workday``greenhouse``lever``ashby``smartrecruiters``oraclecloud``successfactors``icims``workable``bamboohr``teamtailor``paylocity``adp``paycom``ukg``jazzhr``dayforce``recruitee``breezy``personio``jobvite``pinpoint``rippling``applicantpro``peopleadmin``isolvedhire``usajobs``gem``governmentjobs``schooljobs``taleo``manatal``jsonld_sitemap``zohorecruit``comeet``jobscore``ycombinator` `exclude_sources`string\[\] Drop jobs from these applicant-tracking systems, or whose apply link is on one, e.g. \['manatal'\] (its boards are mostly recruiting agencies). `industry`string\[\] Company industry contains ANY (LinkedIn industry names). `exclude_industry`string\[\] Drop companies whose industry contains ANY of these. Jobs whose industry is unknown are kept. `skills`string\[\] The job lists ANY of these skills (whole skill, case-insensitive). `company_size`string\[\] Company headcount bucket(s). Unknown size is excluded. `1``2-10``11-50``51-200``201-500``501-1000``1001-5000``5001-10000``10000+` `exclude_agencies`boolean Drop staffing and recruiting agencies. `sector`string\[\] Company sector(s), from our company profile (98.7% of jobs). `AGRICULTURE``CONSTRUCTION_AND_REAL_ESTATE``CONSUMER_GOODS``EDUCATION``ENERGY``FINANCIAL_SERVICES``GOVERNMENT``HARDWARE_AND_ELECTRONICS``HEALTHCARE``HOSPITALITY``INSURANCE``MANUFACTURING``MEDIA_AND_ENTERTAINMENT``NONPROFIT``OTHER``PHARMA_AND_BIOTECH``PROFESSIONAL_SERVICES``RETAIL``SOFTWARE``STAFFING``TELECOMMUNICATIONS``TRANSPORTATION_AND_LOGISTICS` `company_kind`string\[\] Kind of employer: OPERATING\_COMPANY, CONSULTING, STAFFING\_AGENCY … `CONSULTING``EDUCATION``GOVERNMENT``HEALTH_PROVIDER``NONPROFIT``OPERATING_COMPANY``STAFFING_AGENCY` `customer`string\[\] Who the company sells to. `B2B``B2C``B2G``BOTH` `ownership`string\[\] PUBLIC, PRIVATE, NONPROFIT … Companies with unknown ownership are excluded. `EDUCATION``GOVERNMENT``NONPROFIT``PRIVATE``PUBLIC` `work_mode`string\[\] ANY of: On-site (the posting never mentions remote, hybrid or work from home, or its text says the job is on site), Remote OK (it mentions remote anywhere and its text does not say the job is hybrid or on site), Remote Solely (title or location says remote, same exception), Hybrid (title or location says hybrid, or its text does). All four = no filter. `On-site``Hybrid``Remote OK``Remote Solely` `exclude_work_mode`string\[\] Drop jobs matching ANY of these work modes (same rules as work\_mode). \['Remote Solely'\] keeps every job someone could go in to. `On-site``Hybrid``Remote OK``Remote Solely` `description`string\[\] The title or full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `exclude_description`string\[\] Drop jobs whose full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `taxonomies`string\[\] Job category, Fantastic's names. Read from the job's function flags, the company's sector or kind, and title words; any one is enough. `Technology``Healthcare``Management & Leadership``Finance & Accounting``Human Resources``Sales``Marketing``Customer Service & Support``Education``Legal``Engineering``Science & Research``Trades``Construction``Manufacturing``Logistics``Creative & Media``Hospitality``Retail``Data & Analytics``Software``Energy``Agriculture``Government & Public Sector``Art & Design``Transportation``Consulting` `education`string\[\] The job's requirements ask for ANY of these. `high school``associate degree``bachelor degree``professional certificate``postgraduate degree` `visa`string only = the job offers visa sponsorship (the company sponsors, or the posting says so, and the posting never refuses); exclude = it does not. `only``exclude` `remote_friendly`boolean true = the posting mentions remote/hybrid/WFH anywhere; false = it does not. Prefer work\_mode. `countries`string\[\] ISO-3166 alpha-2 country codes. `locations`string\[\] ANY of these places. Each is 'City, State', 'State' or 'City'; every comma part must match. US states in full or as postal codes. `exclude_locations`string\[\] Drop jobs in ANY of these places (same rules as locations). `experience`string\[\] Years of experience asked for. Postings that do not say are kept. `0-2``2-5``5-10``10+` `employment_type`string\[\] Employment type. Postings that do not say are kept. `FULL_TIME``PART_TIME``CONTRACTOR``TEMPORARY``INTERN` `min_salary_annual`number Published annual pay at least this much. Postings that publish no pay are kept; add has\_salary=true to drop them. Estimates never count. `has_salary`boolean Only jobs whose posting states pay. `posted_within_days`integer 1-365 Posted (or first seen) in the last N days, today included. `posted_since`date (YYYY-MM-DD) Posted (or first seen) on or after this date, YYYY-MM-DD. `posted_before`date (YYYY-MM-DD) Posted (or first seen) before this date, YYYY-MM-DD. `include_internships`boolean Internships and co-ops are included by default; false leaves them out. bash ``` curl -s "https://jobs-api.arihaan.ai/v1/jobs/count?title=Nurse&locations=Texas" -H "Authorization: Bearer $MOBIUS_JOBS_KEY" ``` Example response json ``` { "count": 4812 } ``` --- # Get a job: job postings API Source: https://jobs.arihaan.ai/docs/api/get-job One job in full, including `description_text`, requirements and responsibilities. GET`/v1/jobs/{id}` Parameters `id`string (path)required The job id. URL-encode it: ids contain `:` and sometimes `/`. bash ``` curl -s "https://jobs-api.arihaan.ai/v1/jobs/greenhouse%3Aacmecloud%3A7234001" -H "Authorization: Bearer $MOBIUS_JOBS_KEY" ``` A job that has closed returns `404 not_found`. Closed jobs are removed nightly. --- # Get jobs in batch: job postings API Source: https://jobs.arihaan.ai/docs/api/batch Up to 100 full jobs in one request, in the order asked. POST`/v1/jobs/batch` Body `ids`string\[\] (1-100)required Job ids from a search. bash ``` curl -s -X POST https://jobs-api.arihaan.ai/v1/jobs/batch -H "Authorization: Bearer $MOBIUS_JOBS_KEY" \ -H "Content-Type: application/json" -d '{"ids": ["greenhouse:acmecloud:7234001", "workday:globex:R-1182"]}' ``` Example response json ``` { "jobs": [ { "id": "greenhouse:acmecloud:7234001", … } ], "missing": ["workday:globex:R-1182"] } ``` --- # Meta: job postings API Source: https://jobs.arihaan.ai/docs/api/meta Every filter with its allowed values, and live facts about the data. Free. GET`/v1/meta`free: not counted Example response json ``` { "filters": [ { "name": "work_mode", "type": "list", "values": ["On-site", "Hybrid", "Remote OK", "Remote Solely"], … } ], "metrics": { "by_source": [ … ], "top_countries": [ … ] } } ``` --- # Usage: job postings API Source: https://jobs.arihaan.ai/docs/api/usage Your tokens today and this month, your limits, and a 30-day series. Free. GET`/v1/usage`free: not counted Example response json ``` { "tokens_today": 18400, "tokens_month": 212300, "daily_token_limit": 500000, "concurrent_limit": 5, "today": 42, "month": 318, "day_resets_at": "2026-09-29T00:00:00+00:00", "month_resets_at": "2026-10-01T00:00:00+00:00", "series": [ { "day": "2026-09-28", "tokens": 18400, "requests": 42, "api": 30, "mcp": 12 }, … ] } ``` `today` and `month` are request counts, for your own records; the limit is in tokens. --- # Companies: job postings API Source: https://jobs.arihaan.ai/docs/api/companies Company profiles: size, headcount, revenue range, funding, founded, headquarters and who is hiring for what, right now. ## Get a company GET`/v1/companies/{name or slug}` Pass a name (`Stripe`) or a LinkedIn slug (`stripe`). The `hiring` block is live: open jobs, newest posting, top locations, countries and titles. bash ``` curl -s "https://jobs-api.arihaan.ai/v1/companies/stripe" -H "Authorization: Bearer $MOBIUS_JOBS_KEY" ``` Example response json ``` { "slug": "stripe", "name": "Stripe", "website": "https://stripe.com", "linkedin_url": "https://www.linkedin.com/company/stripe", "industry": "Technology, Information and Internet", "size": "5001-10000", "headcount": 17172, "headquarters": "South San Francisco, California", "founded": "2010", "type": "Privately Held", "followers": 1667032, "is_staffing_agency": false, "revenue_usd": { "min": 500000000, "max": 1000000000 }, "funding_total_usd": null, "hiring": { "open_jobs": 412, "newest_posting": "2026-09-27", "top_locations": [ { "value": "San Francisco, CA", "jobs": 96 }, … ], "top_countries": [ { "value": "US", "jobs": 301 }, … ], "top_titles": [ { "value": "Account Executive", "jobs": 14 }, … ], "by_experience": [ … ], "remote_friendly_jobs": 88, "sources": ["greenhouse"] } } ``` ## Find companies GET`/v1/companies` Parameters `name`string Name contains this. `industry`string Industry contains this, e.g. Software. `company_size`string\[\] Headcount buckets. `1``2-10``11-50``51-200``201-500``501-1000``1001-5000``5001-10000``10000+` `hiring_only`boolean Only companies with open jobs (default true). `limit`integer 1-50 How many (default 20). Most-followed first. bash ``` curl -s "https://jobs-api.arihaan.ai/v1/companies?industry=Software&company_size=51-200,201-500" -H "Authorization: Bearer $MOBIUS_JOBS_KEY" ``` ## Company data on every job Add `include_company=true` to a search to attach the full profile to each job as `company`. Full jobs (`/v1/jobs/{id}`, batch) always include it. About half of all jobs match a company profile. Revenue is LinkedIn’s estimate (about 80% filled); funding is filled for few companies. --- # Filters Source: https://jobs.arihaan.ai/docs/filters All optional, combined with AND. A list matches ANY of its values. The same filters work in the API, the MCP tools and the playground. 35 filters `title`string\[\] Title has ANY of these as words, case and punctuation ignored; the last word may continue ('Product Lead' finds 'Product Leader'). `title_exclude`string\[\] Drop jobs whose title contains ANY of these. `title_whole_words`boolean Match title and title\_exclude as whole words only: the last word is not continued ('Lead' does not find 'Leader'). Words are always whole: 'CTO' never finds 'Director', excluding 'IT' keeps 'Security Analyst'. `company`string\[\] Only these companies (substring of the company name or its board key). `exclude_company`string\[\] Drop these companies (substring match). `sources`string\[\] Only jobs from these applicant-tracking systems, or whose apply link is on one (an employer's career site whose Apply goes to its Workday board matches 'workday'). `workday``greenhouse``lever``ashby``smartrecruiters``oraclecloud``successfactors``icims``workable``bamboohr``teamtailor``paylocity``adp``paycom``ukg``jazzhr``dayforce``recruitee``breezy``personio``jobvite``pinpoint``rippling``applicantpro``peopleadmin``isolvedhire``usajobs``gem``governmentjobs``schooljobs``taleo``manatal``jsonld_sitemap``zohorecruit``comeet``jobscore``ycombinator` `exclude_sources`string\[\] Drop jobs from these applicant-tracking systems, or whose apply link is on one, e.g. \['manatal'\] (its boards are mostly recruiting agencies). `industry`string\[\] Company industry contains ANY (LinkedIn industry names). `exclude_industry`string\[\] Drop companies whose industry contains ANY of these. Jobs whose industry is unknown are kept. `skills`string\[\] The job lists ANY of these skills (whole skill, case-insensitive). `company_size`string\[\] Company headcount bucket(s). Unknown size is excluded. `1``2-10``11-50``51-200``201-500``501-1000``1001-5000``5001-10000``10000+` `exclude_agencies`boolean Drop staffing and recruiting agencies. `sector`string\[\] Company sector(s), from our company profile (98.7% of jobs). `AGRICULTURE``CONSTRUCTION_AND_REAL_ESTATE``CONSUMER_GOODS``EDUCATION``ENERGY``FINANCIAL_SERVICES``GOVERNMENT``HARDWARE_AND_ELECTRONICS``HEALTHCARE``HOSPITALITY``INSURANCE``MANUFACTURING``MEDIA_AND_ENTERTAINMENT``NONPROFIT``OTHER``PHARMA_AND_BIOTECH``PROFESSIONAL_SERVICES``RETAIL``SOFTWARE``STAFFING``TELECOMMUNICATIONS``TRANSPORTATION_AND_LOGISTICS` `company_kind`string\[\] Kind of employer: OPERATING\_COMPANY, CONSULTING, STAFFING\_AGENCY … `CONSULTING``EDUCATION``GOVERNMENT``HEALTH_PROVIDER``NONPROFIT``OPERATING_COMPANY``STAFFING_AGENCY` `customer`string\[\] Who the company sells to. `B2B``B2C``B2G``BOTH` `ownership`string\[\] PUBLIC, PRIVATE, NONPROFIT … Companies with unknown ownership are excluded. `EDUCATION``GOVERNMENT``NONPROFIT``PRIVATE``PUBLIC` `work_mode`string\[\] ANY of: On-site (the posting never mentions remote, hybrid or work from home, or its text says the job is on site), Remote OK (it mentions remote anywhere and its text does not say the job is hybrid or on site), Remote Solely (title or location says remote, same exception), Hybrid (title or location says hybrid, or its text does). All four = no filter. `On-site``Hybrid``Remote OK``Remote Solely` `exclude_work_mode`string\[\] Drop jobs matching ANY of these work modes (same rules as work\_mode). \['Remote Solely'\] keeps every job someone could go in to. `On-site``Hybrid``Remote OK``Remote Solely` `description`string\[\] The title or full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `exclude_description`string\[\] Drop jobs whose full description contains ANY of these, as whole words (case-insensitive). Needs title or company in the same search. `taxonomies`string\[\] Job category, Fantastic's names. Read from the job's function flags, the company's sector or kind, and title words; any one is enough. `Technology``Healthcare``Management & Leadership``Finance & Accounting``Human Resources``Sales``Marketing``Customer Service & Support``Education``Legal``Engineering``Science & Research``Trades``Construction``Manufacturing``Logistics``Creative & Media``Hospitality``Retail``Data & Analytics``Software``Energy``Agriculture``Government & Public Sector``Art & Design``Transportation``Consulting` `education`string\[\] The job's requirements ask for ANY of these. `high school``associate degree``bachelor degree``professional certificate``postgraduate degree` `visa`string only = the job offers visa sponsorship (the company sponsors, or the posting says so, and the posting never refuses); exclude = it does not. `only``exclude` `remote_friendly`boolean true = the posting mentions remote/hybrid/WFH anywhere; false = it does not. Prefer work\_mode. `countries`string\[\] ISO-3166 alpha-2 country codes. `locations`string\[\] ANY of these places. Each is 'City, State', 'State' or 'City'; every comma part must match. US states in full or as postal codes. `exclude_locations`string\[\] Drop jobs in ANY of these places (same rules as locations). `experience`string\[\] Years of experience asked for. Postings that do not say are kept. `0-2``2-5``5-10``10+` `employment_type`string\[\] Employment type. Postings that do not say are kept. `FULL_TIME``PART_TIME``CONTRACTOR``TEMPORARY``INTERN` `min_salary_annual`number Published annual pay at least this much. Postings that publish no pay are kept; add has\_salary=true to drop them. Estimates never count. `has_salary`boolean Only jobs whose posting states pay. `posted_within_days`integer 1-365 Posted (or first seen) in the last N days, today included. `posted_since`date (YYYY-MM-DD) Posted (or first seen) on or after this date, YYYY-MM-DD. `posted_before`date (YYYY-MM-DD) Posted (or first seen) before this date, YYYY-MM-DD. `include_internships`boolean Internships and co-ops are included by default; false leaves them out. ## Rules worth knowing - **Unstated passes.** `experience`, `employment_type` and `min_salary_annual` keep postings that don’t say. Most postings don’t state experience; dropping them would hide most jobs. - **Published pay only.** Salary filters use pay the employer published, never an estimate. Add `has_salary=true` to require it. - **Work mode is read from the posting.** Remote Solely and Hybrid come from the title or location; Remote OK means the posting mentions remote anywhere. - **Internships are included.** Set `include_internships=false` to leave them out. - **Exclusions are exact complements.** Including and excluding the same value always add up to the total. ## Recipes ### Fresh remote roles with pay query ``` title=Software Engineer&work_mode=Remote Solely&posted_within_days=3&has_salary=true ``` ### Senior roles in two cities, no agencies query ``` title=Product Manager&experience=5-10,10+&locations=Austin, Texas&locations=Denver, CO&exclude_agencies=true ``` ### Big companies hiring Python skills query ``` skills=Python&company_size=5001-10000,10000+&countries=US ``` --- # The job object Source: https://jobs.arihaan.ai/docs/job-object Field names follow common job-feed conventions, so most integrations map directly. | Field | Type | Meaning | | --- | --- | --- | | `id` | string | Stable id: vendor:tenant:source\_job\_id | | `title` | string | Job title | | `organization` | string | Company name | | `apply_url, url` | string | The employer’s application page | | `source` | string | workday, greenhouse, lever, ashby … | | `date_posted, date_first_seen` | date | Freshness filters use posted, else first seen | | `locations_derived, cities_derived, regions_derived, countries_derived` | string\[\] | Where the job is | | `remote_friendly` | boolean | The posting mentions remote, hybrid or work from home | | `ai_experience_level` | string | null | 0-2, 2-5, 5-10, 10+ or not stated | | `ai_employment_type` | string\[\] | FULL\_TIME, PART\_TIME, CONTRACTOR, TEMPORARY, INTERN | | `has_salary` | boolean | The employer published pay | | `ai_salary_min_value, ai_salary_max_value` | number | null | Published pay, annualized | | `ai_salary_currency, ai_salary_unit_text` | string | null | Currency; unit is YEAR after annualizing | | `estimated_pay` | object | A model estimate for display. Never used by filters | | `org_linkedin_industry, org_linkedin_size` | string | null | Company industry and headcount bucket, where matched | | `organization_url, organization_logo, org_linkedin_slug` | string | null | Company website, logo and LinkedIn slug | | `ai_key_skills` | string\[\] | Skills named in the posting | | `department, seniority` | string | null | As stated by the employer | | `requisition_id` | string | null | The employer’s own job number | | `last_seen_at` | date | When we last saw the posting live | | `salary_period` | string | null | The pay period the employer published | | `description_text, ai_requirements_summary, ai_core_responsibilities` | string | Full text (full job, or include\_description=true) | | `job_function, job_language` | string | null | Job function and posting language (full job) | | `ai_flags` | object | Model-read yes/no facts: is\_senior, has\_equity, degree\_required, travel\_required… Display only; may be wrong | | `company` | object | null | Full [company profile](https://jobs.arihaan.ai/docs/api/companies) (full job, or include\_company=true) | Example response json ``` { "id": "greenhouse:acmecloud:7234001", "title": "Senior Data Engineer", "organization": "Acme Cloud", "organization_url": "https://acme.example", "organization_logo": "https://…/logo.png", "org_linkedin_industry": "Software Development", "org_linkedin_size": "1001-5000", "url": "https://boards.greenhouse.io/acmecloud/jobs/7234001", "apply_url": "https://boards.greenhouse.io/acmecloud/jobs/7234001", "source": "greenhouse", "date_posted": "2026-09-26", "date_first_seen": "2026-09-27", "locations_derived": ["Remote, United States"], "countries_derived": ["US"], "remote_friendly": true, "ai_experience_level": "5-10", "ai_employment_type": ["FULL_TIME"], "has_salary": true, "ai_salary_min_value": 170000, "ai_salary_max_value": 210000, "ai_salary_currency": "USD", "ai_salary_unit_text": "YEAR", "ai_key_skills": ["Python", "SQL", "Spark", "Airflow"] } ``` --- # Coverage and freshness Source: https://jobs.arihaan.ai/docs/coverage Where the jobs come from and where they are. | | | | --- | --- | | Open jobs | … | | Countries | … | | Employers | … | | Updated | Daily | ## Top sources | Source | Share of jobs | | --- | --- | | workday | 30% | | greenhouse | 10% | | smartrecruiters | 8% | | lever | 7% | | ashby | 5% | ## Top countries | Country | Share of jobs | | --- | --- | | US | 54% | | GB | 4.1% | | IN | 3.5% | | CA | 3.4% | | FR | 3.2% | | DE | 3.2% | | AU | 1.4% | | SG | 1% | | ES | 0.9% | | CN | 0.8% | --- # Paging Source: https://jobs.arihaan.ai/docs/paging Results are newest first. Page with cursors: they never skip or repeat a job, even while the index changes. 1. 1 Call search with a `limit` (1-100). 2. 2 If `next_cursor` is not null, call again with `cursor=` and the same filters. 3. 3 Stop when `next_cursor` is `null`. python ``` cursor, jobs = None, [] while True: params = {"title": "Nurse", "countries": "US", "limit": 100} if cursor: params["cursor"] = cursor page = requests.get("https://jobs-api.arihaan.ai/v1/jobs", params=params, headers=H).json() jobs += page["jobs"] cursor = page["next_cursor"] if not cursor: break ``` `offset` (up to 5,000) also works, for clients built around it, but can’t be combined with `cursor`. --- # Errors Source: https://jobs.arihaan.ai/docs/errors One shape everywhere. The code is stable; the message is written for a person and names the problem. json ``` { "error": { "code": "invalid_request", "message": "posted_within_days must be 1-365" } } ``` | Status | Code | When | | --- | --- | --- | | 400 | `invalid_request` | A filter name or value is wrong (unknown parameters are errors too) | | 400 | `too_broad` | The search covers too many jobs to answer; add a title, company or location | | 401 | `unauthorized` | Missing, mistyped or revoked key | | 404 | `not_found` | The job closed, or the id is wrong | | 429 | `limit_reached` | Too many at once, or the daily or monthly limit; see Retry-After | | 5xx | | Our side. Retry with backoff | In MCP, the same problems come back as a tool error with the same message, so the model can fix its own arguments. --- # OpenAPI Source: https://jobs.arihaan.ai/docs/openapi An OpenAPI 3.1 document for Postman, SDK generators and Custom GPT Actions. No key needed to read it. url ``` https://jobs-api.arihaan.ai/v1/openapi.json ``` ## Custom GPT Actions 1. 1 In ChatGPT: Explore GPTs → Create → Configure → Create new action. 2. 2 Import from URL: paste the address above. 3. 3 Authentication: API Key, auth type Bearer, paste your key. --- # Changelog Source: https://jobs.arihaan.ai/docs/changelog ## 2026-09-28 - Public beta: REST API, MCP server with OAuth for ChatGPT and Claude, dashboard, keys and docs. - New filters: `posted_within_days`, `posted_before`, `skills`, `exclude_industry`, `exclude_locations`. - New MCP tools: `describe_catalog`, `search`, `fetch`, `get_company`, `find_companies`. - Company profiles (`/v1/companies`) with revenue, funding, headcount and live hiring; `include_company` on searches. - Full jobs add `requisition_id`, `last_seen_at`, `job_function`, `job_language` and `ai_flags`. --- # FAQ Source: https://jobs.arihaan.ai/docs/faq ### Is this scraped from job boards? No. Jobs come from employers’ own applicant-tracking systems, and each links to the employer’s application page. ### How often is it updated? Nightly. Closed jobs are removed in the same run. ### Does a search returning 100 jobs cost more than one returning 1? Yes. Bigger answers use more tokens, so ask for the number of jobs you need. ### Can I use it in Claude or ChatGPT without code? Yes. See [ChatGPT](https://jobs.arihaan.ai/docs/connect/chatgpt) or [Claude](https://jobs.arihaan.ai/docs/connect/claude). ### Can I get more? Yes. Every plan is a number of tokens a day; pick a bigger plan at jobs.arihaan.ai/pricing or contact us at rey.hanoko@mobiusengine.ai. ### How do I change or cancel my plan? From Billing in your dashboard. An upgrade starts right away and you pay only the difference for the rest of the month; a smaller plan starts at your next renewal, with no credit, and you keep your current plan until then. Cancel keeps your plan on until the end of the month you paid for. You can also download your invoices there. ### Do you store my prompts? We record each request in full: the tool or endpoint, every filter and parameter sent, and what we returned. We do not see your wider conversation unless the app puts it in a request.