HitPrace MCP: Czech jobs and market snapshots in your AI app

Add HitPrace to your AI app

1. 1Click Connect HitPrace free. There's no sign-in, so its tools are ready at once.
2. 2The server is read-only and all seven tools start on. If you don't look up employers, switch off the company tools such as `find_companies` and `get_company_jobs` to keep your AI app's tool list short.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app for developer jobs in Brno, then find that search in Activity.

Czech job market questions

• Search Czech job listings by place, occupation or employer with `search_jobs`.
• Ask how many offers there are and what they pay with `get_job_market_snapshot`, without pulling every listing.
• Find an employer with `find_companies` and list its open jobs.
• Read a job ad in full, with a link to cite.

Visibility for a read-only server

• A HitPrace tool you switch off disappears from your AI apps.
• Activity records each search made through ContextGate.

What you get with HitPrace and ContextGate

• Your AI apps can use HitPraceClaude, Cursor, ChatGPT and other AI apps reach HitPrace through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any HitPrace tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

HitPrace tools

Examples of what your AI apps can do in HitPrace. You'll see the exact list of tools after you connect it.

• search_jobsConcrete job cards. For a count or salary question use get_job_market_snapshot. A search needs location, lat with lng, occupation, q, or company_sef. company_sef from find_companies combines with location, occupation, salary, feature and employment. Do not count jobs. jobs[] is one page, not a sample of the whole match, so do not rank employers, occupations or market shares from it. Cite a job by
• get_jobJob metadata. Full text is the canonical url with Accept text/markdown, or get_job_public_content. Cite a job by url, id, title, employer name and place. Cite matching_active_jobs with retrieved_at. Cite salary only when the salary object is present, with period, currency, sample_size and salary.updated_at. methodology_url belongs to aggregated interpretation. The page length is not the job count.
• get_job_public_contentOne public job as markdown. Returns id, url and markdown. The url is the canonical detail.
• get_job_market_snapshotCount and salary without cards. Prefer this when the user asks how many offers or what pay is offered. With no filters it is the whole public HitPrace dataset in the Czech Republic: active deduplicated offers on HitPrace.cz, not a census of every vacancy in Czechia, and it has no salary. company_sef is allowed. A missing salary object means the sample is unpublished. Cite a job by url, id, title,
• find_companiesResolve a human employer name. At most five profiles. Do not guess when several are plausible. A brand is not the legal employer.
• get_companyPublic employer profile for a sef returned by find_companies. Do not invent the sef. Cite a job by url, id, title, employer name and place. Cite matching_active_jobs with retrieved_at. Cite salary only when the salary object is present, with period, currency, sample_size and salary.updated_at. methodology_url belongs to aggregated interpretation. The page length is not the job count. Do not aggreg
• get_company_jobsJob cards for one known employer when no other filter is requested. If the user also wants location, occupation, salary, feature or employment, call search_jobs with company_sef from find_companies. Cite a job by url, id, title, employer name and place. Cite matching_active_jobs with retrieved_at. Cite salary only when the salary object is present, with period, currency, sample_size and salary.upd