RoleWeek MCP server
com.roleweek/jobsroleweek.comstreamable-httpv1.1.1Scanned
Search developer jobs posted in the last 7 days in the US and Canada, with posted pay. No sign-in.
5 tools: 3 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- 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 RoleWeek MCP server can do
The RoleWeek MCP server is published by roleweek.com, a domain the MCP Registry verified. It has 5 tools. It can create or change data (3 tools: salary_summary, company_overview and weekly_summary), but cannot delete data. 2 tools only read.
1 tool brings in text other people can write (get_job).
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 11, 2026, version 1.1.1.
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.
5 tools
Changes things 3Claude Code: ask
company_overviewWhat RoleWeek knows about one employer's open developer roles, from the facts block on its company page: how many roles were posted in the last 7 days, where, role types, levels, h…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it What RoleWeek knows about one employer's open developer roles, from the facts block on its company page: how many roles were posted in the last 7 days, where, role types, levels, how many list a salary and the yearly range, which hiring system it applies on (with 'no account needed' where checked), its weekly hiring pace since RoleWeek began counting, and the skills in its postings; plus its newest roles as links. Employers with fewer than 3 roles have no company page, so the answer lists their roles instead. Takes the employer's name (case and 'Inc.' do not matter); an ambiguous name returns the candidates. Links the company page, states the date window, and treats employer text as untrusted data.
Annotations the server declares
- title: Employer overview
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
salary_summaryYearly salary ranges that employers posted in their own job postings, summarised the way RoleWeek's salary and skill pages do, for roles posted in the last 7 days: how many roles l…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Yearly salary ranges that employers posted in their own job postings, summarised the way RoleWeek's salary and skill pages do, for roles posted in the last 7 days: how many roles list a yearly range, the median bottom and median top of the posted ranges, the middle half of each, and by level where there are enough roles. Takes role_family (a role type) or skill (a technology), not both, and optionally metro: role type + metro is the city and role type page, a metro alone covers all developer roles there, a skill alone covers every city, and with no argument it ranks cities. Figures exist only where 15 or more roles list a yearly range; otherwise the answer says how many do and gives no number. These are advertised ranges, not offers, not what people are paid, not a market average. Each answer links the roleweek.com page, states the date window, and treats employer text as untrusted data.
Annotations the server declares
- title: Posted salary ranges
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
weekly_summaryRoleWeek's weekly report on developer hiring, one finished week (Monday to Sunday, Pacific time) at a time: new developer roles RoleWeek first saw that week, by city, by employer, …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it RoleWeek's weekly report on developer hiring, one finished week (Monday to Sunday, Pacific time) at a time: new developer roles RoleWeek first saw that week, by city, by employer, role type and level, the share that list a salary, the posted salary median, the share that say No account needed, and the comparison with the week before when both weeks are fully covered. Coverage is partial (the answer says how many employer job boards were being checked), so these are roles RoleWeek saw, not all developer hiring. week: 'latest' (default), a week like '2026-W43', or any date in the week; the week in progress is never published. Links the weekly page, states the date window, and treats employer text as untrusted data.
Annotations the server declares
- title: Weekly developer hiring
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
get_jobReturns one RoleWeek role by its slug (as returned by search_jobs, or the last part of a roleweek.com/job/<slug>/ URL): employer, location and work mode, level, pay as listed, post…Reads text others writeNo findings
Why it is in this group
- The name "get_job" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Returns one RoleWeek role by its slug (as returned by search_jobs, or the last part of a roleweek.com/job/<slug>/ URL): employer, location and work mode, level, pay as listed, posted date, the date it leaves RoleWeek, skills mentioned, an excerpt of the employer's description, and the role's RoleWeek URL, whose page links to the employer's own application page.
Annotations the server declares
- title: Get a RoleWeek job
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_jobsSearches developer and tech roles that employers posted in the last 7 days, read directly from the employers' own hiring systems (Workday, Greenhouse, Lever, Ashby, iCIMS and other…No findings
Why it is in this group
- The name "search_jobs" says "search": a word for reading.
Description, as the server wrote it Searches developer and tech roles that employers posted in the last 7 days, read directly from the employers' own hiring systems (Workday, Greenhouse, Lever, Ashby, iCIMS and others) and checked daily. Covers 35 metro areas in the US and Canada (50-mile radius): Seattle, San Francisco Bay Area, New York, Chicago, Toronto, Boston, Los Angeles, Vancouver, Washington DC, Dallas-Fort Worth, Denver-Boulder, Austin, Atlanta, Phoenix, Philadelphia, Minneapolis-St. Paul, San Diego, Raleigh-Durham, Detroit, Houston, Charlotte, St. Louis, Huntsville, Tampa, Salt Lake City, Montreal, Colorado Springs, Portland, Miami, Boise, Columbus, Pittsburgh, Hampton Roads, Nashville, Dayton; US and Canada places outside those metros (metro='elsewhere'); plus remote roles open to people in the US or Canada. Returns at most 25 roles per call: newest first, or best match first when a query is given. Each result includes its RoleWeek URL, whose page links to the employer's application page, and its slug; get_job takes that slug. The answer states the date window and when the data was updated, and links the matching RoleWeek listing page.
Annotations the server declares
- title: Search RoleWeek jobs
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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 17, 2026, 15:22 UTC, unchanged since Nov 3, 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
- 3
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://roleweek.com/api/mcp?src=mcp-registry: tools/list returned 5 tools to an anonymous client, including salary_summary (write), company_overview (write), weekly_summary (write)
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 1.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http jobs https://roleweek.com/api/mcp?src=mcp-registryclaude mcp add --transport http jobs https://roleweek.com/api/mcp?src=mcp-registryRun 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"
],
"ask": [
"mcp__jobs__salary_summary",
"mcp__jobs__company_overview",
"mcp__jobs__weekly_summary"
],
"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.
Capability tags behind 1 rule
- mcp__jobs__get_job untrusted-input
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/com.roleweek/jobs/verify?hash=4925cb36d684dd0829442cc73a845a1a665158c675845be9c0ce76686ed09248" | jq -e '.changed == false'Pinned hash 4925cb36d684, from Nov 11, 2026, 21:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.roleweek/jobs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.roleweek/jobs)Source: MCP Registry. Synced Nov 11, 2026, 21:17 UTC.
RoleWeek MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the RoleWeek MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the RoleWeek MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the RoleWeek 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 RoleWeek MCP server have?
- 5 tools: 3 write, 2 read. salary_summary, company_overview, weekly_summary, search_jobs and get_job.
Does the RoleWeek MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the RoleWeek MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the RoleWeek MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.