ats-jobs-mcp
Provides search and discovery of open jobs from Greenhouse company career sites via the ATS Jobs Feed, including keyword, country, remote, seniority, and posting-date filters plus company hiring signals.
Provides search and discovery of open jobs from Personio company career sites via the ATS Jobs Feed, including keyword, country, remote, seniority, and posting-date filters plus company hiring signals.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
ats-jobs-mcp
MCP server that gives an AI agent a daily-refreshed index of 350k+ open jobs from 12,000+ company career sites (Greenhouse, Lever, Ashby, SmartRecruiters, Recruitee, Personio). It calls the ATS Jobs Feed Apify Actor (pay per result, hard cost cap per call).
Tools
search_jobs(keywords, country, remote_only, seniority, posted_within_days, limit)new_jobs_since(days, keywords, country, limit): what opened since yesterdaycompany_hiring_signals(function, min_open_jobs, limit): who is hiring most this week
Related MCP server: simplyapply-jobs-mcp
Install
# run directly from GitHub (no PyPI package is published yet)
uvx --from git+https://github.com/best-apis/ats-jobs-mcp ats-jobs-mcp
# or: pip install git+https://github.com/best-apis/ats-jobs-mcpClaude Desktop / Cursor config:
{ "mcpServers": { "ats-jobs": { "command": "uvx", "args": ["--from", "git+https://github.com/best-apis/ats-jobs-mcp", "ats-jobs-mcp"], "env": { "APIFY_TOKEN": "<your token>" } } } }Get a token from a free Apify account (Settings, API & integrations). ATS_JOBS_MAX_COST_USD (default 1.0) caps spend per tool call.
Note: the ats-jobs-mcp name on PyPI belongs to an unrelated project, so install from this repo as shown above.
Prefer no local install? Use the hosted Apify MCP server: https://mcp.apify.com?tools=best_apis/ats-jobs-feed.
MIT licensed. Data: public job-board endpoints; employers can request removal via the Actor's Issues tab.
Related MCP Connectors
1.2M+ jobs from employer career sites, salary benchmarks and company hiring signals for AI agents.
Open jobs from Greenhouse, Lever, Ashby and 4 more ATSs in one schema, with new-job monitoring.
A jobs data API and MCP server. Every listing comes from the employer's own career site, an ATS feed or a government employment service, never resold from another board. Each row names its source and when we last confirmed the vacancy existed, and a role that disappears keeps a closure date and a reason. Six tools: search_jobs, get_job, company_hiring, market_signals, coverage, changes_since.
Company hiring signals + open jobs from Greenhouse, Lever, Ashby boards, API + MCP. 20 free/day.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to pull live job listings from major ATS platforms (Greenhouse, Lever, Ashby, Workable), Hacker News hiring threads, and detect hiring signals on company career pages.-
- AlicenseAqualityCmaintenanceEnables real-time job search across thousands of companies' open roles from Greenhouse, Lever, Ashby, and SmartRecruiters, with full-text filtering and company-specific queries, no API key required.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables searching live job postings pulled directly from 10 applicant-tracking-system APIs — including Greenhouse, Lever, Ashby, Workday, Personio, Recruitee, Teamtailor, Workable, SmartRecruiters and Breezy HR — using just a company website, domain or ATS handle, with filters for keywords, location, remote work and posting date. Also supports multi-company lookups, ATS detection, and stateless "only new since last call" monitoring for scheduled agents.MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to search salary-transparent tech job postings across nine boards and eight countries, filter them by pay, remote work, tech stack, level, and language, and retrieve apply URLs or track applications. All commands are JSON-first, so duplicates and unfilterable criteria come back as data rather than errors.-