Skip to content

jobstack-mcp server

io.github.IsaiahDupree/jobstack-mcpIsaiahDupreestreamable-httpv1.0.0Scanned

Unified jobs search over official feeds + ATS boards (USAJOBS, Adzuna, Muse, Greenhouse, Lever...)

2 tools: 2 only read.

Tools: 0 delete, 0 irreversible, 0 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

Run the operations that matter as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the jobstack-mcp server can do

The jobstack-mcp server is published by the GitHub account IsaiahDupree. It has 2 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

2 tools bring in text other people can write (search_jobs and 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 2, 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.

2 tools

Only reads 2Show 2 read-only tools
  • get_jobFetch one job posting by its source engine and native id, returned as { meta, job } with the same flat Job shape search_jobs yields.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 server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Fetch one job posting by its source engine and native id, returned as { meta, job } with the same flat Job shape search_jobs yields. The id is the native upstream id as returned by that source in search results (NOT prefixed with the source name). Exception: for source="ats" the id is a composite "board:company:nativeId" string (e.g. "greenhouse:airbnb:7995153") so the lookup can round-trip to the right ATS board. Not every source supports single-job lookup — a search-only source returns a not_supported / not_found error.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • search_jobsSearch job postings across every configured source and merge the results into one flat Job shape.Reads text others writeNo findings

    Why it is in this group

    • The name "search_jobs" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Search job postings across every configured source and merge the results into one flat Job shape. Fans out in parallel to USAJOBS, Adzuna, Jooble, The Muse, Reed, and the ats engine (Greenhouse/Lever/Ashby/Workable/SmartRecruiters), then merges + sorts by postedDate (newest first) and paginates the combined set. Each Job has id, source, title, company, location, remote, url, description, postedDate, salaryMin, salaryMax, salaryCurrency, department, and employmentType. The response envelope carries meta, the echoed query, sources_requested, an optional sources_errored map, total, count, limit, offset, and results. Use sources= to restrict to specific engines.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:58 UTC, unchanged since Nov 20, 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

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 503 to 200
    • tools/list served without credentials: no to yes
    • Protocol version: none to 2025-06-18
  2. Nov 13, 2026
    • HTTP status of an anonymous initialize: 200 to 503
    • tools/list served without credentials: yes to no
    • Protocol version: 2025-06-18 to none

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.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 503 -> 200; tools/list served without credentials: no -> yes; Protocol version: none -> 2025-06-18.View diff
    • HTTP status of an anonymous initialize: 503 to 200
    • tools/list served without credentials: no to yes
    • Protocol version: none to 2025-06-18
  2. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 503; tools/list served without credentials: yes -> no; Protocol version: 2025-06-18 -> none.View diff
    • HTTP status of an anonymous initialize: 200 to 503
    • tools/list served without credentials: yes to no
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http jobstack https://jobstack-mcp.vercel.app/mcp
claude mcp add --transport http jobstack https://jobstack-mcp.vercel.app/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__jobstack__search_jobs",
      "mcp__jobstack__get_job"
    ],
    "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 jobstack. Review it before you use it.

Capability tags behind 2 rules
  • mcp__jobstack__search_jobs untrusted-input
  • mcp__jobstack__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/io.github.IsaiahDupree/jobstack-mcp/verify?hash=7e005d449d1dbd5f41ebaf286861ecf805f6333bac75a7d937f4cd3e173d4a7b" | jq -e '.changed == false'

Pinned hash 7e005d449d1d, from Nov 2, 2026, 15:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.IsaiahDupree/jobstack-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.IsaiahDupree/jobstack-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.IsaiahDupree/jobstack-mcp.svg)](https://radar.anlyon.com/servers/io.github.IsaiahDupree/jobstack-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:16 UTC.

jobstack-mcp server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the jobstack-mcp server safe?

No scan can promise that. What its definitions show: 2 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 jobstack-mcp server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the jobstack-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 jobstack-mcp server have?

2 tools: 2 read. search_jobs and get_job.

Does the jobstack-mcp server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the jobstack-mcp server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the jobstack-mcp server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 2, 2026.