A local job-search workspace for agents: vacancy search, CV matching, application pipeline, interviews and offers.
Job hunting produces a lot of state. Saved vacancies, three versions of a CV, recruiter emails, interview dates, two offers with different payment terms. The Worklife MCP server gives an agent a structured place to keep all of it, plus tools to go and find more, while your personal data stays in a workspace on your own machine.
It is aimed at an individual job seeker who already works inside an MCP client such as Claude Code, Cursor, Codex or OpenCode. The model runs in your client; Worklife supplies the tools and storage. An optional built-in runner can drive its own loop if you point it at an OpenAI-compatible endpoint, but nothing is configured or called by default.
Tools in the Worklife MCP server are grouped by stage of the search:
market_collect, market_snapshot and market_report gather explicit queries and report salary medians and quantiles, kept separate by currency, pay period and gross or netrecommendations_report, cv_match and recommendation_save compare vacancies with your stated conditions and experience factspipeline_update, inbox_sync and conversation_update track stages, next steps and linked repliesinterview_brief, interview_save, offer_save and offer_compareemployer_block keeps a personal blocklist; automation_configure schedules recurring checksRecording an offer does not accept it, and saving an interview sends no invitation. CVs import from TXT, Markdown, PDF with a text layer, or DOCX, and export to Markdown, HTML or PDF.
Python 3.12 or newer and uv are needed. The quickest route is the setup command with a target for your client, for example --target claude-code or --target cursor. It builds a persistent runtime, installs Chromium for browser automation and prepares a career folder in your home directory. Open that folder in your client and begin with recruiter_start.
For an existing stdio client you can instead run the pinned worklife-recruiter mcp entry through uvx, which stores data in ~/.worklife. Browser features then need the browser extra and Chromium installed separately.
Accounts on job sites, email (SMTP and IMAP) and a Telegram bot are configured by you; there is no universal access to platforms. Passwords created by credential_create live in the system keychain, and there is no unencrypted fallback. A shared, signed knowledge base of employer observations syncs in the background; only employer information goes there, not your profile. Much of the detailed documentation is in Russian. Related tools include Adzuna Job Search and the wider HR and recruiting category.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| recruiter_start | Starting point for a session; the agent asks about your job-search goals. |
| market_collect | Collect vacancies for explicitly chosen search queries. |
| market_snapshot | Save an immutable sample of collected vacancies. |
| market_report | Report salary coverage, medians, quantiles and source limits, split by currency, period and tax basis. |
| job_save | Save a vacancy found through the browser so it can join a sample. |
| recommendations_report | Check vacancies against your conditions and experience facts. |
| cv_match | Compare CV versions against a vacancy. |
| pipeline_update | Update an application's stage, next step and deadline. |
| inbox_sync | Store incoming email and link replies to applications. |
| interview_brief | Prepare questions and materials for an interview from the vacancy and your experience. |
| offer_compare | Compare saved offers, including terms and payment timing. |
| cv_export | Export a CV to Markdown, HTML or PDF. |
| employer_block | Add a company to your personal blocklist so it is excluded from results and contact. |
| automation_configure | Schedule recurring search refreshes, inbox checks and reviews. |
{
"mcpServers": {
"worklife_recruiter": {
"command": "uvx",
"args": [
"--python",
"3.12",
"--from",
"worklife-agent==0.5.2",
"worklife-recruiter",
"mcp"
]
}
}
}Needs uv and Python 3.12+. Data is stored in ~/.worklife. Browser automation additionally needs the browser extra and Chromium.
| Variable | Description | Required |
|---|---|---|
| WORKLIFE_HOME | Overrides where personal data is stored (default ~/.worklife). | Optional |
| WORKLIFE_NETWORK_OFFLINE | Set to 1 to stop update checks against PyPI. | Optional |
| WORKLIFE_AGENT_BASE_URL | Endpoint of an OpenAI-compatible service for the optional built-in agent runner. | Optional |
| WORKLIFE_AGENT_MODEL | Model name for the optional built-in runner. | Optional |
| WORKLIFE_AGENT_API_KEY | API key for the built-in runner's endpoint, if it needs one. | Optional |
| WORKLIFE_NETWORK_GITHUB_TOKEN | Token used to publish employer observations to the shared knowledge base; an existing gh auth login also works. | Optional |
Enables AI assistants to interact with the Loxo recruitment platform API for managing candidates, jobs, and activities.
Official MCP server for 100Hires ATS: candidates, jobs, applications, interviews, messages.
Read-only Workday for Claude — fetch tasks, pay, benefits via your signed-in session
【Every star you give feeds a hungry developer's motivation!⭐️】A Model Context Protocol (MCP) server implementation that provides Google Jobs search
Scans Greenhouse, Lever, Ashby, Workday, Rippling for roles in any category. Clay-ready.
Combines hiring and tech-stack signals into one composite GTM score. Clay-ready output.