Skip to content

workman.rent — humans for real-world checks MCP server

rent.workman/workmanworkman.rentstreamable-httpv0.2.1Scanned

Hire verified people to call a business, photo a storefront or check a shelf price. Free sandbox.

5 tools: 4 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 4 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 5
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

4 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.
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 workman.rent — humans for real-world checks MCP server can do

The workman.rent — humans for real-world checks MCP server is published by workman.rent, a domain the MCP Registry verified. It has 5 tools. It can create or change data (4 tools: start_pairing, pairing_status, sandbox_signup_start and sandbox_signup_verify), but cannot delete data. 1 tool only reads.

5 tools bring in text other people can write (start_pairing, pairing_status, list_task_templates and 2 more).

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 21, 2026, version 0.2.1.

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 4Claude Code: ask
  • pairing_statusStep 2 of onboarding.Reads text others writeNo findings

    Why it is in this group

    • The name "pairing_status" says "status": a word for reading.
    • The input takes a statement or command to run (input.code), which can change anything it can reach.

    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
    Step 2 of onboarding. While pending returns { status }. When the requester has confirmed, returns { status: "ready", client_id, api_key } exactly ONCE — store them. Then reconnect to https://workman.rent/mcp with header Authorization: Bearer <client_id>:<api_key> to get the task tools (no header support, e.g. Claude.ai / ChatGPT connectors: use the returned connector_url as the connector URL).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • sandbox_signup_startTry workman.rent in 5 minutes without business verification (KYB): the SANDBOX runs the full task flow (create → fund → accept → submit → confirm, same statuses and webhooks as pro…Reads text others writeNo findings

    Why it is in this group

    • The name "sandbox_signup_start" says "start": a word for a change.

    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
    Try workman.rent in 5 minutes without business verification (KYB): the SANDBOX runs the full task flow (create → fund → accept → submit → confirm, same statuses and webhooks as production) but tasks are taken by a bot and payments are simulated; no real people, no real money. Ask your human operator for their email, call this, then ask them for the 6-digit code from the email and call sandbox_signup_verify. Returns: { sent: true }

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • sandbox_signup_verifyConfirms the 6-digit code and returns { client_id, api_key: "sk_sandbox_…" } ONCE — store them.Reads text others writeNo findings

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.

    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
    Confirms the 6-digit code and returns { client_id, api_key: "sk_sandbox_…" } ONCE — store them. Calling it again for the same email issues a new key and disables the old one. accept_rules must be true: your human operator accepts the Platform Rules (https://workman.rent/oferta.html) — ask them before you send it. Then reconnect to https://workman.rent/mcp with header Authorization: Bearer <client_id>:<api_key> (or stdio env WORKMAN_CLIENT_ID / WORKMAN_API_KEY). Client cannot set headers (Claude.ai / ChatGPT custom connector)? Use the returned connector_url as the connector URL. Returns: { sandbox: true, client_id, api_key, connector_url, limits, quickstart, go_live }

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • start_pairingStep 1 of onboarding.Reads text others writeNo findings

    Why it is in this group

    • The name "start_pairing" says "start": a word for a change.

    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
    Step 1 of onboarding. Returns a short code (valid 15 min). Show it to your human operator: a VERIFIED requester confirms it in the dashboard at https://workman.rent/zamovnik.html. Then call pairing_status with the code. There is no anonymous self-registration. No verified requester yet? Try the SANDBOX first (sandbox_signup_start): full task flow with a bot, no verification. Returns: { code, expires_in, poll_after, instruction }

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • list_task_templatesCatalogue of ready-made task templates (call_check, storefront_photo, shelf_price_check, store_open_check).Reads text others writeNo findings

    Why it is in this group

    • The name "list_task_templates" says "list": 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
    Catalogue of ready-made task templates (call_check, storefront_photo, shelf_price_check, store_open_check). Each has a result spec (checklist questions, minimum photos, done-when), a recommended and minimum budget in USDC, the executor skill, the location type and a default deadline. Create a task from one with create_task { template_id, purpose, place or lat/lng, + your own description where required }. No account needed. Read-only. Returns: { templates: [{ id, title, summary, recommended_budget_usdc, min_budget_usdc, required_skill, location_type, remote, default_deadline_hours, result_spec, required_fields }] }

    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 write5
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 21, 2026, 19:20 UTC, unchanged since Nov 21, 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
  • WarnThe whole server

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

    Matched text

    https://workman.rent/mcp: tools/list returned 5 tools to an anonymous client, including start_pairing (write), pairing_status (write), sandbox_signup_start (write), sandbox_signup_verify (write)

    What this check looks for

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 0.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http workman https://workman.rent/mcp
claude mcp add --transport http workman https://workman.rent/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__workman__list_task_templates"
    ],
    "ask": [
      "mcp__workman__start_pairing",
      "mcp__workman__pairing_status",
      "mcp__workman__sandbox_signup_start",
      "mcp__workman__sandbox_signup_verify"
    ],
    "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 workman. Review it before you use it.

Capability tags behind 5 rules
  • mcp__workman__start_pairing untrusted-input
  • mcp__workman__pairing_status untrusted-input
  • mcp__workman__list_task_templates untrusted-input
  • mcp__workman__sandbox_signup_start untrusted-input
  • mcp__workman__sandbox_signup_verify 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/rent.workman/workman/verify?hash=532e424d10cc45e9eebae00e76923911bdf76a5a2a19e7d8a4c40e4f02600c39" | jq -e '.changed == false'

Pinned hash 532e424d10cc, from Nov 21, 2026, 17:18 UTC.

Watch

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

https://radar.anlyon.com/servers/rent.workman/workman/changes.xml

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

Badge

Anlyon Radar badge for rent.workman/workman
[![Anlyon Radar](https://radar.anlyon.com/badge/rent.workman/workman.svg)](https://radar.anlyon.com/servers/rent.workman/workman)

Source: MCP Registry. Synced Nov 21, 2026, 17:18 UTC.

workman.rent — humans for real-world checks MCP server: questions and answers

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

Is the workman.rent — humans for real-world checks MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 4 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 workman.rent — humans for real-world checks MCP server delete data?

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

Can the workman.rent — humans for real-world checks 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 workman.rent — humans for real-world checks MCP server have?

5 tools: 4 write, 1 read. start_pairing, pairing_status, sandbox_signup_start, sandbox_signup_verify and list_task_templates.

Does the workman.rent — humans for real-world checks MCP server need sign-in or OAuth?

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

Does the workman.rent — humans for real-world checks MCP server send data to outside services?

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

Has the workman.rent — humans for real-world checks MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.