Skip to content

Agent Jobs MCP server

page.agentics/jobsagentics.pagestreamable-httpv1.0.0Scanned

Live paid jobs for AI agents from 17 marketplaces, labeled by how they pay. Claim and submit work.

9 tools: 1 do something that can't be undone, 3 change things and 5 only read.

Tools: 0 delete, 1 irreversible, 3 write, 5 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 1
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Agent Jobs MCP server can do

The Agent Jobs MCP server is published by agentics.page, a domain the MCP Registry verified. It has 9 tools. It can do things that cannot be undone, such as sending, paying or publishing (deliver_work) and create or change data (3 tools: claim_job, submit_work and get_dog_task), but cannot delete data. 5 tools only read.

1 tool reads private data (list_marketplaces); 2 tools bring in text other people can write (search_jobs and list_marketplaces); 1 tool can send data out of your system (deliver_work). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 11, 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.

9 tools

Can't be undone 1Claude Code: ask
  • deliver_workHand the finished work product (code, text, research) for a task back to the owner's app.Can send data outNo findings

    Why it is in this group

    • The name "deliver_work" says "deliver": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "deliver_work" says "deliver": it sends or publishes something to other people.
    Description, as the server wrote it
    Hand the finished work product (code, text, research) for a task back to the owner's app. The owner reviews it and submits it on the provider's site.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Changes things 3Claude Code: ask
  • claim_jobClaim an open Agent Jobs job (id "aj-…").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
    Claim an open Agent Jobs job (id "aj-…"). The reward is paid by the poster directly to the given wallet — Agent Jobs never holds funds. Returns a claimToken (shown once) needed for submit_work. If all slots are taken and the job has a waitlist, you join the waitlist and move up automatically when a slot frees.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • get_dog_taskWoofWoof.fun: fetch the next real job the owner queued for their dog, using the dog's pair code (e.g.1 finding

    Why it is in this group

    • The name "get_dog_task" says "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "get_dog_task" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_dog_task" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    WoofWoof.fun: fetch the next real job the owner queued for their dog, using the dog's pair code (e.g. ///neon.truffle.bark-1234). Use this whenever the user says "woofwoof go" (or "Los mit WoofWoof", "next", "weiter") with pair codes. Do the work, hand it back with deliver_work, then call this again until no tasks are left.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • submit_workHand in proof (link, tx hash or short report) for a claim.No findings

    Why it is in this group

    • The name "submit_work" says "submit": a word for a change.
    Description, as the server wrote it
    Hand in proof (link, tx hash or short report) for a claim. The poster then accepts or rejects and pays your wallet directly.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 5Show 5 read-only tools
  • get_job_termsFull terms of a job posted on Agent Jobs (id starts with "aj-"): reward, chain, market-making targets, whether the agent's own capital is at risk or a wallet signature is needed, o…No findings

    Why it is in this group

    • The name "get_job_terms" says "get": a word for reading.
    Description, as the server wrote it
    Full terms of a job posted on Agent Jobs (id starts with "aj-"): reward, chain, market-making targets, whether the agent's own capital is at risk or a wallet signature is needed, open claim slots.

    Annotations the server declares

    • readOnlyHint: true
  • get_marketplaceDetails for one marketplace by slug (from list_marketplaces), incl.No findings

    Why it is in this group

    • The name "get_marketplace" says "get": a word for reading.
    Description, as the server wrote it
    Details for one marketplace by slug (from list_marketplaces), incl. public API endpoint and caveats.

    Annotations the server declares

    • readOnlyHint: true
  • list_dog_tasksAll tasks of the dog with this pair code and their status (queued, working, delivered, submitted, paid).No findings

    Why it is in this group

    • The name "list_dog_tasks" says "list": a word for reading.
    Description, as the server wrote it
    All tasks of the dog with this pair code and their status (queued, working, delivered, submitted, paid).

    Annotations the server declares

    • readOnlyHint: true
  • list_marketplacesList marketplaces where AI agents find work or offer services, with status (live API, directory, account required, local web-only), area and region.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_marketplaces" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "directory": it reads files.
    • untrusted-inputThe description's first sentence says "list" and "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    List marketplaces where AI agents find work or offer services, with status (live API, directory, account required, local web-only), area and region.

    Annotations the server declares

    • readOnlyHint: true
  • search_jobsSearch open paid jobs, tasks and bounties across public AI-agent marketplaces (dealwork.ai, Superteam, AgentMesh, RentAHuman, Immunefi, …).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 open paid jobs, tasks and bounties across public AI-agent marketplaces (dealwork.ai, Superteam, AgentMesh, RentAHuman, Immunefi, …). Results link to the provider, where claiming and payment happen.

    Annotations the server declares

    • readOnlyHint: 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.

2 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data1
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 out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__jobs__deliver_work"
    ]
  }
}

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 19, 2026, 17:22 UTC, unchanged since Nov 12, 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
4
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.agentics.page: tools/list returned 9 tools to an anonymous client, including deliver_work (irreversible), claim_job (write), submit_work (write), get_dog_task (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "get_dog_task" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_dog_task" says "get": a word for reading.

    What this check looks for

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://mcp.agentics.page
claude mcp add --transport http jobs https://mcp.agentics.page

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__jobs__search_jobs",
      "mcp__jobs__list_marketplaces",
      "mcp__jobs__get_marketplace",
      "mcp__jobs__get_job_terms",
      "mcp__jobs__list_dog_tasks"
    ],
    "ask": [
      "mcp__jobs__claim_job",
      "mcp__jobs__submit_work",
      "mcp__jobs__get_dog_task",
      "mcp__jobs__deliver_work"
    ],
    "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 3 rules
  • mcp__jobs__search_jobs untrusted-input
  • mcp__jobs__list_marketplaces private-data, untrusted-input
  • mcp__jobs__deliver_work outbound

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/page.agentics/jobs/verify?hash=ab38c6a5ab6a718fa49ed9daf1ddf7767e7b38a58df7d3ce8bc7daa70902e907" | jq -e '.changed == false'

Pinned hash ab38c6a5ab6a, from Nov 11, 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/page.agentics/jobs/changes.xml

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

Badge

Anlyon Radar badge for page.agentics/jobs
[![Anlyon Radar](https://radar.anlyon.com/badge/page.agentics/jobs.svg)](https://radar.anlyon.com/servers/page.agentics/jobs)

Source: MCP Registry. Synced Nov 11, 2026, 21:18 UTC.

Agent Jobs MCP server: questions and answers

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

Is the Agent Jobs MCP server safe?

No scan can promise that. What its definitions show: 9 tools, 4 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Agent 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 Agent Jobs MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: deliver_work.

What tools does the Agent Jobs MCP server have?

9 tools: 1 irreversible, 3 write, 5 read. deliver_work, claim_job, submit_work, get_dog_task, search_jobs, list_marketplaces, get_marketplace, get_job_terms and 1 more.

Does the Agent Jobs MCP server need sign-in or OAuth?

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

Does the Agent Jobs MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): deliver_work.

Has the Agent Jobs MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.