workman.rent — humans for real-world checks
Server Details
Hire verified people to call a business, photo a storefront or check a shelf price. Free sandbox.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
The two onboarding paths (start_pairing/pairing_status vs sandbox_signup_start/sandbox_signup_verify) are parallel flows that could be confused at a glance, but descriptions explicitly label one as SANDBOX and cross-reference each other ('No verified requester yet? Try the SANDBOX first'). list_task_templates is clearly separate and read-only. Boundaries are workable, though the agent must read carefully to pick the right flow.
All snake_case and readable, but conventions mix: verb_noun (list_task_templates, start_pairing), noun_state (pairing_status), and prefixed flow pairs (sandbox_signup_start/verify). The asymmetry between 'start_pairing' and 'pairing_status' for two halves of the same flow is the weakest point, though the sandbox pair is internally consistent.
Five tools covering an unauthenticated bootstrap layer is tight and well-scoped: one catalogue plus a start/poll pair per flow. The two-tool-per-flow pattern is justified by polling and OTP verification, so nothing feels padded, though the duplicated sandbox flow adds mild redundancy.
The server's stated domain is real-world task checking, yet no task lifecycle tools are present here — no create_task, fund, list/status, accept, or submit — only onboarding and template listing, with the real tools gated behind an auth reconnect. An agent cannot accomplish the core purpose with this surface, and even the template listing lacks a detail/get counterpart.
Available Tools
5 toolslist_task_templatesList ready-made task templatesARead-onlyIdempotentInspect
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 }] }
Inputs: no named parameters.
pairing_statusPoll pairing status; returns client_id + api_key ONCEAInspect
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).
Inputs: code (required).
sandbox_signup_startGet a SANDBOX key, step 1 (no business verification)AInspect
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 }
Inputs: email (required).
sandbox_signup_verifyGet a SANDBOX key, step 2: email code → client_id + sk_sandbox_ keyAInspect
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 }
Inputs: code (required), email (required), accept_rules (required).
start_pairingGet a pairing code (onboarding, no account needed)AInspect
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 }
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hire real people for AI data collection (photos, audio, video), app testing and microtasks.
Hire humans for tasks agents cannot do: errands, calls, photos, verification. Escrowed, verified.
Your AI agent hires real people for phone calls, errands, photos and store checks. Paid upfront into escrow, released only when the proof checks out. 20% fee ($2 minimum), no subscription.
Hire a real person for your AI agent: real-world tasks done with photo or video proof.
Related MCP Servers
AlicenseAqualityCmaintenanceEnables AI agents to hire verified human operators for tasks requiring physical presence, human perception, or judgment, such as real-world verification, product testing, and data collection.6MIT
humanforaiofficial
AlicenseAqualityCmaintenanceEnables AI agents to hire real human operators for tasks requiring physical presence, human perception, or judgment, such as verification, testing, data collection, and physical-world tasks.459 npm1MIT- AlicenseAqualityBmaintenanceLast-mile human work for AI agents. Phone calls, physical-world tasks, captcha on an already-authorized account, subjective QA, and long manual work, done by real virtual assistants.1385 npmMIT
- AlicenseAqualityCmaintenanceReal human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.747 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.