AI Dev Jobs MCP server
com.aidevboard/jobsaidevboard.comstreamable-httpv1.6.2Scanned
MCP for 8,700+ current AI jobs. 13 tools: search, match, salaries, companies, commerce quotes.
20 tools: 7 change things and 13 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
7 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 AI Dev Jobs MCP server can do
The AI Dev Jobs MCP server is published by aidevboard.com, a domain the MCP Registry verified. It has 20 tools. It can create or change data (7 tools: match_jobs, compile_job_specific_resume, approve_compiled_application, apply_to_job and 3 more), but cannot delete data. 13 tools only read.
2 tools bring in text other people can write (get_job and get_company).
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 12, 2026, version 1.6.2.
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.
20 tools
Changes things 7Claude Code: ask
apply_to_jobSubmit only the exact, visible compiled artifact after the email-verified human principal approves its hash.No findings
Why it is in this group
- The name "apply_to_job" says "apply": a word for a change.
Description, as the server wrote it Submit only the exact, visible compiled artifact after the email-verified human principal approves its hash. Requires the single-use approval authorization, an API key, and principal_authorized=true. Candidates and agents are never charged.
approve_compiled_applicationCreate a short-lived, single-use authorization for one email-verified candidate, one exact compiled artifact hash, and one unchanged active job.No findings
Why it is in this group
- The name "approve_compiled_application" says "approve": a word for a change.
Description, as the server wrote it Create a short-lived, single-use authorization for one email-verified candidate, one exact compiled artifact hash, and one unchanged active job. Requires principal_authorized=true, costs the candidate $0, and does not submit an application.
compile_job_specific_resumeCompile a $0 candidate-controlled ATS-oriented plain-text Markdown resume for one active job using only candidate-verified evidence.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.
Description, as the server wrote it Compile a $0 candidate-controlled ATS-oriented plain-text Markdown resume for one active job using only candidate-verified evidence. Without identity, returns a transient non-persisted preview that cannot be approved or submitted. With a verified candidate key, saves an immutable draft hash plus a machine-readable candidate_review handoff and requires the agent to pause for explicit human review. Never submits or authorizes an application.
match_jobsRank active AI/ML jobs against a candidate profile for free.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.
Description, as the server wrote it Rank active AI/ML jobs against a candidate profile for free. Scoring combines tag overlap (+2 per match), salary overlap (+3), workplace/level/type/location matches, and description keyword hits. After selecting a role, candidates may use compile_job_specific_resume for a $0 transient ATS-oriented preview without identity; a verified key is required only to save an approval-bound artifact. The employer outcome pilot never affects these matches.
record_my_application_outcomeRecord one email-verified candidate's explicitly authorized, fixed-taxonomy application outcome for $0.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.
Description, as the server wrote it Record one email-verified candidate's explicitly authorized, fixed-taxonomy application outcome for $0. The receipt is candidate-reported, not employer-verified, creates no acceptance-rate claim, and never changes organic ranking.
respond_to_interview_outcomeRecord the authenticated candidate's independent response to an employer-reported interview.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.
Description, as the server wrote it Record the authenticated candidate's independent response to an employer-reported interview. Requires explicit principal authorization. Confirmation can make a fixed employer fee billable; candidates and agents pay $0.
start_checkoutReturns a non-charging owner-review request template for the Verified Interview Pilot only.No findings
Why it is in this group
- The name "start_checkout" says "start": a word for a change.
Description, as the server wrote it Returns a non-charging owner-review request template for the Verified Interview Pilot only. It creates no request, program, candidate action, invoice, or charge. Employer identity, exact-role authority, and acknowledgement of the capped 30-day terms are required before a separate review request may be submitted.
Only reads 13Show 13 read-only tools
analyze_application_readinessAnalyze candidate-verified evidence against one active job for $0 without requiring identity.No findings
Why it is in this group
- The name "analyze_application_readiness" says "analyze": a word for reading.
Description, as the server wrote it Analyze candidate-verified evidence against one active job for $0 without requiring identity. The transient response reports covered and unsupported public job signals without an acceptance probability, does not persist candidate evidence, does not submit an application, and rejects hidden screening-model instructions.
get_companyGet detailed profile for an AI company: total open roles, salary range, top tags/skills, workplace distribution, and apply URL.Reads text others writeNo findings
Why it is in this group
- The name "get_company" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Get detailed profile for an AI company: total open roles, salary range, top tags/skills, workplace distribution, and apply URL. Use after list_companies or search_jobs to learn more about a specific employer.
get_jobFetch full job posting by ID or slug: title, description, requirements, salary, workplace, tags, apply URL.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 "fetch" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch full job posting by ID or slug: title, description, requirements, salary, workplace, tags, apply URL. Use after search_jobs to read a specific listing.
get_salary_dataSalary benchmarks for AI/ML roles.No findings
Why it is in this group
- The name "get_salary_data" says "get": a word for reading.
Description, as the server wrote it Salary benchmarks for AI/ML roles. Filter by tag (e.g. 'llm', 'pytorch'), experience level, workplace type, or company. Returns average, median, p25, p75, min, max, and sample count. Useful for compensation research and negotiation.
get_similar_jobsGiven a job ID or slug, return active jobs that match on tag overlap, same workplace, level, and job type.No findings
Why it is in this group
- The name "get_similar_jobs" says "get": a word for reading.
Description, as the server wrote it Given a job ID or slug, return active jobs that match on tag overlap, same workplace, level, and job type. Ranked by similarity score (tag overlap weighted 3x). Use after search_jobs to surface nearby roles — matches the /jobs/{id}/similar REST endpoint.
get_statsCurrent AI Dev Jobs index statistics: total active jobs, companies hiring, median salary, new jobs today / this week, and the top 10 trending tags across jobs posted in the last 7 …No findings
Why it is in this group
- The name "get_stats" says "get": a word for reading.
Description, as the server wrote it Current AI Dev Jobs index statistics: total active jobs, companies hiring, median salary, new jobs today / this week, and the top 10 trending tags across jobs posted in the last 7 days. This is free index data and does not create a payment handoff.
get_trending_companiesCompanies posting the most AI/ML jobs in the last N days.No findings
Why it is in this group
- The name "get_trending_companies" says "get": a word for reading.
Description, as the server wrote it Companies posting the most AI/ML jobs in the last N days. Complements get_stats trending_tags_7d — while that answers 'what skills are trending', this answers 'who's hiring most aggressively'. Returns company name/slug/logo plus the count of new jobs in the window.
list_companiesReturns top AI/ML companies by active role count, optionally with average salary.No findings
Why it is in this group
- The name "list_companies" says "list": a word for reading.
Description, as the server wrote it Returns top AI/ML companies by active role count, optionally with average salary. Useful for discovering who is hiring in AI.
list_my_interview_outcomesList employer-reported interview outcomes for applications submitted with the authenticated developer API key.No findings
Why it is in this group
- The name "list_my_interview_outcomes" says "list": a word for reading.
Description, as the server wrote it List employer-reported interview outcomes for applications submitted with the authenticated developer API key. No candidate fee is ever created.
list_productsReturns AI Dev Board's only agent-readable commercial offer: the employer-funded Verified Interview Pilot.No findings
Why it is in this group
- The name "list_products" says "list": a word for reading.
Description, as the server wrote it Returns AI Dev Board's only agent-readable commercial offer: the employer-funded Verified Interview Pilot. Candidates and agents pay $0; job discovery and the evidence-backed application workflow are free. The pilot is billable only after an owner-approved program, a verified candidate-authorized application, and independent employer and candidate interview confirmation. It never changes organic ranking.
list_tagsReturns all available job tags/skills with the count of active jobs for each.No findings
Why it is in this group
- The name "list_tags" says "list": a word for reading.
Description, as the server wrote it Returns all available job tags/skills with the count of active jobs for each. Use to discover what tags are available for search_jobs filtering.
quote_productReturns the deterministic, outcome-only terms for AI Dev Board's Verified Interview Pilot.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns the deterministic, outcome-only terms for AI Dev Board's Verified Interview Pilot. No candidate or agent is charged; legacy package, sponsorship, and Dossier product IDs are retired from agent commerce.
search_jobsSearch curated AI/ML engineering roles for free.No findings
Why it is in this group
- The name "search_jobs" says "search": a word for reading.
Description, as the server wrote it Search curated AI/ML engineering roles for free. Filter by tags (e.g. llm, pytorch), workplace (remote/hybrid/onsite), global remote eligibility, experience level, salary range, or keyword. After selecting a role, candidates may use compile_job_specific_resume for a $0 transient ATS-oriented preview without identity; a verified key is required only to save an approval-bound artifact. The employer outcome pilot never affects organic results.
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 write2
- 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, 18:33 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
- 7
- 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 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://aidevboard.com/mcp: tools/list returned 20 tools to an anonymous client, including match_jobs (write), compile_job_specific_resume (write), approve_compiled_application (write), apply_to_job (write), record_my_application_outcome (write) and 2 more
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 1.6.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http jobs https://aidevboard.com/mcpclaude mcp add --transport http jobs https://aidevboard.com/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__list_companies",
"mcp__jobs__get_company",
"mcp__jobs__get_stats",
"mcp__jobs__get_salary_data",
"mcp__jobs__get_similar_jobs",
"mcp__jobs__get_trending_companies",
"mcp__jobs__list_tags",
"mcp__jobs__analyze_application_readiness",
"mcp__jobs__list_my_interview_outcomes",
"mcp__jobs__list_products",
"mcp__jobs__quote_product"
],
"ask": [
"mcp__jobs__match_jobs",
"mcp__jobs__compile_job_specific_resume",
"mcp__jobs__approve_compiled_application",
"mcp__jobs__apply_to_job",
"mcp__jobs__record_my_application_outcome",
"mcp__jobs__respond_to_interview_outcome",
"mcp__jobs__start_checkout"
],
"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 2 rules
- mcp__jobs__get_job untrusted-input
- mcp__jobs__get_company 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.aidevboard/jobs/verify?hash=4c86ce5be39eedd751654a8a6e6941028987c1226de630f837cbf2a4865c6f10" | jq -e '.changed == false'Pinned hash 4c86ce5be39e, from Nov 12, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.aidevboard/jobs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.aidevboard/jobs)Source: MCP Registry. Synced Oct 21, 2026, 17:48 UTC.
AI Dev Jobs MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AI Dev Jobs MCP server safe?
- No scan can promise that. What its definitions show: 20 tools, 7 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 AI Dev Jobs MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AI Dev Jobs 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 AI Dev Jobs MCP server have?
- 20 tools: 7 write, 13 read. match_jobs, compile_job_specific_resume, approve_compiled_application, apply_to_job, record_my_application_outcome, respond_to_interview_outcome, start_checkout, search_jobs and 12 more.
Does the AI Dev Jobs MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AI Dev Jobs MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AI Dev Jobs MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.