mcpbeat Sign in

Physical Agency MCP Server

answering

Physical Agency is answering right now. Last checked moments ago. It exposes 6 tools.

Human workforce for AI agents: field checks, user testing and device tests. Operator-reviewed work.

Uptime history 61 hours of history
61 hours agonow
100.0%
Uptime 24h
92 of 92 checks
6
Tools
read from the server
450 ms
Response time
average over 24h
open, no key
Access
streamable-http

What changed 4

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 10 October 2026. No other catalogue keeps this.

10 Oct 3 tool descriptions were rewritten get_product, list_skills, search_workers
10 Oct a tool changed the parameters it asks for search_workers

Nothing serious here today

Today is the operative word: we check Physical Agency every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

run in your terminal
claude mcp add manpower --transport http https://physical-agency-141382386601.asia-southeast1.run.app/api/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "manpower": {
      "url": "https://physical-agency-141382386601.asia-southeast1.run.app/api/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.manpower]
url = "https://physical-agency-141382386601.asia-southeast1.run.app/api/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "manpower": {
      "url": "https://physical-agency-141382386601.asia-southeast1.run.app/api/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "manpower": {
      "url": "https://physical-agency-141382386601.asia-southeast1.run.app/api/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

capabilities
get_capabilities
Read what this human workforce pool does, task categories, lifecycle, terms, prohibited uses and limits. Call this first.
product
get_product
Read product request conditions, completion criteria, consultation checks, related products and discovery guidance by stable productId (e.g. LAB01, TRD001). Set locale=en for English or ko for Korean. Research rank is not availability.
products
list_products
Search the product catalog by Korean or English discovery terms, family or group. Paginated; use nextOffset. Includes agent tasks and traditional staffing (driving, housekeeping, construction, etc). Listings require consultation and do not confirm available workers, prices or booking.
skills
list_skills
List skills, languages, categories and countries actually present in the active pool, with worker counts. Use these values in search_workers.
worker
get_worker_profile
Read one anonymous worker profile by handle (e.g. "w-7kq2xm").
workers
search_workers
Search anonymous worker profiles worldwide by skills, languages, category, remote/on-site location, verification and budget. Results are ranked with explainable match reasons. Use skillsMatch=all for strict skill requirements, or rank for partial matches. weeklyWindow requires stated local weekly hours covering the whole window. Searching does not reserve anyone.

Endpoints

URLTransportStateLatencyChecked
https://physical-agency-141382386601.asia-southeast1.run.app/api/mcp streamable-http answering 411 ms 0 min ago

Alternatives to Physical Agency

same job, measured the same way
Human For AI
by humanforai

Hire a real human for real-world verification, product testing, AI output review, and errands.

45 installs/wk 6 tools answering
Currents
by currents

Self-healing CI tests and proof of work for AI agents

answering
Colter
by mfbahc

Colter audits product pages for AI shopping agents and returns fixes, tests, and Evidence Packs.

33 installs/wk local only
Random Profiles
by random-profiles

Generate fake user profiles and companies for tests, seed data, and AI agent demos.

62 installs/wk local only
Keploy
by keploy

End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.

7 tools answering
Rigor MCP
by mrnh

Verified statistical inference for AI agents: hypothesis tests, sequential testing, power.

143 installs/wk local only
Synthetic Data — Random User
by saifs

Generate synthetic random user data for testing, demos, and development without using real persona.

answering
API Tester
by ryudi84

MCP server for API testing: HTTP requests, cURL generation, health checks.

28 installs/wk local only

Physical Agency — questions

Answers built from our own checks of this server.

What can Physical Agency do?
It exposes 6 tools, read directly from the server on our last check. Among them: get_capabilities, get_product, get_worker_profile, list_products, list_skills, search_workers. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Physical Agency working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 450 ms. The bar chart above shows every period we have measured.
How do I connect Physical Agency?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Physical Agency need an API key?
No. Physical Agency completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Physical Agency?
It answers our handshake in 450 ms on average, which is faster than 30% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.