Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@jobs-scrape-mcp What skills are most in demand in Geneva?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP (Model Context Protocol) server exposing the jobs-scrape corpus to an AI.
Once connected, Claude can directly query the collected job postings: “what skills are requested in the canton of Vaud?”, “how many part-time job postings in healthcare in August?”, “summarize this posting”.
uv pip install git+https://github.com/XavierBeheydt/jobs-scrape-mcp.git
claude mcp add jobs-scrape -- uv run jobs-scrape-mcpThe server reads the same database as the CLI:
Variable | Default |
|
|
|
|
Related MCP server: mcp-jobs
Tool | When to call it |
| Any question about job postings, requested skills, observed salaries, or a company's activity |
| Read one full posting, after finding it |
| Discover what the corpus contains before filtering (cantons, companies, sources) |
| Trend question: what is most in demand, by region or by source |
| Volume of job postings published per day |
| Overview — call first to know what the database contains |
| Where the data comes from, and why an expected source may be missing |
Resources: jobs://summary and jobs://sources.
An MCP tool returns its result in the model's context. Returning twenty complete postings -- several tens of thousands of characters -- would saturate that context for zero benefit: you don't read twenty full descriptions to answer “what skills are requested in Geneva”.
This server therefore applies a simple rule:
list tools return excerpts (320 characters) and the structured fields used to judge relevance;
get_job returns the full text of a single posting;
limit is capped at 50, whatever the requested value;
each response distinguishes total (matches) from returned (items returned), so the model knows it only sees a part.
BM25 ranking, facets, and aggregations live in jobs_scrape.search, at the heart of the project. This module merely exposes them. Search remains defined in a single place — the web interface and the MCP server inherit it, and an improvement to ranking benefits both.
The model chooses its tools based on their description. A description that only says what a tool does leaves the model to guess when to use it. Each tool therefore states its trigger — “call this tool as soon as a question concerns available job postings” — and a test verifies that no description remains sparse.
uv venv
uv pip install git+https://github.com/XavierBeheydt/jobs-scrape.git
uv pip install -e ".[dev]"
uv run pytest -q # hors ligne, base temporaireThis server cannot be deployed
Query professional profiles, search candidates, and get AI-powered summaries and job fit analysis.
Semantic search over 3.5M+ live US job postings pulled straight from company ATSes. Read-only.
AI resume triage for recruiters. Query your candidate pool from Claude or ChatGPT.
Search job postings, companies, and technology stacks across 10M+ companies.
