HitPrace MCP server
cz.hitprace/jobshitprace.czstreamable-httpv1.0.0Scanned
Read-only Czech job search and market snapshots.
7 tools: 7 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the HitPrace MCP server can do
The HitPrace MCP server is published by hitprace.cz, a domain the MCP Registry verified. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 14, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Only reads 7Show 7 read-only tools
find_companiesResolve a human employer name.No findings
Why it is in this group
- The name "find_companies" says "find": a word for reading.
Description, as the server wrote it Resolve 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.No findings
Why it is in this group
- The name "get_company" says "get": a word for reading.
Description, as the server wrote it Public 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 aggregate jobs into a market figure. Do not convert hourly pay to a month. Full job text is the canonical url with Accept: text/markdown.
get_company_jobsJob cards for one known employer when no other filter is requested.No findings
Why it is in this group
- The name "get_company_jobs" says "get": a word for reading.
Description, as the server wrote it Job 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.updated_at. methodology_url belongs to aggregated interpretation. The page length is not the job count. Do not aggregate jobs into a market figure. Do not convert hourly pay to a month. Full job text is the canonical url with Accept: text/markdown.
get_jobJob metadata.No findings
Why it is in this group
- The name "get_job" says "get": a word for reading.
Description, as the server wrote it Job 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. Do not aggregate jobs into a market figure. Do not convert hourly pay to a month. Full job text is the canonical url with Accept: text/markdown.
get_job_market_snapshotCount and salary without cards.No findings
Why it is in this group
- The name "get_job_market_snapshot" says "get": a word for reading.
Description, as the server wrote it Count 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, 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 aggregate jobs into a market figure. Do not convert hourly pay to a month. Full job text is the canonical url with Accept: text/markdown.
get_job_public_contentOne public job as markdown.No findings
Why it is in this group
- The name "get_job_public_content" says "get": a word for reading.
Description, as the server wrote it One public job as markdown. Returns id, url and markdown. The url is the canonical detail.
search_jobsConcrete job cards.No findings
Why it is in this group
- The name "search_jobs" says "search": a word for reading.
Description, as the server wrote it Concrete 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 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 aggregate jobs into a market figure. Do not convert hourly pay to a month. Full job text is the canonical url with Accept: text/markdown.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:51 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http jobs https://www.hitprace.cz/api/v1/mcpclaude mcp add --transport http jobs https://www.hitprace.cz/api/v1/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__jobs__search_jobs",
"mcp__jobs__get_job",
"mcp__jobs__get_job_public_content",
"mcp__jobs__get_job_market_snapshot",
"mcp__jobs__find_companies",
"mcp__jobs__get_company",
"mcp__jobs__get_company_jobs"
],
"ask": [],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as jobs. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/cz.hitprace/jobs/verify?hash=45248aff2f99803ccea00e5b7062bc5b86ca4ce07395450b0a26d0b32302e15f" | jq -e '.changed == false'Pinned hash 45248aff2f99, from Nov 14, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/cz.hitprace/jobs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/cz.hitprace/jobs)Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.
HitPrace MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the HitPrace MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the HitPrace MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the HitPrace MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the HitPrace MCP server have?
- 7 tools: 7 read. search_jobs, get_job, get_job_public_content, get_job_market_snapshot, find_companies, get_company and get_company_jobs.
Does the HitPrace MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the HitPrace MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the HitPrace MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.