# Human For AI

> Human For AI, an MCP server by humanforai.dev, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Hire a real human for real-world verification, product testing, AI output review, and errands.

- Canonical: https://www.anchorterminal.com/tools/humanforai
- Markdown: https://www.anchorterminal.com/tools/humanforai.md (~850 tokens)
- Slim: https://www.anchorterminal.com/tools/humanforai.min.md (~780 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/humanforai.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# Human For AI

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by humanforai.dev (https://humanforai.dev)
- Listed because: It's published in the registry under humanforai.dev, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Hire a real human for real-world verification, product testing, AI output review, and errands.

## Facts

- MCP registry: `dev.humanforai/humanforai` 0.1.4
- Endpoint: https://humanforai.dev/mcp (streamable HTTP)
- Package: npm `humanforai` (stdio)
- Source: https://github.com/humanforai/humanforai-mcp
- Website: https://humanforai.dev
- npm downloads a week: 44
- GitHub stars: 1
- Registry entry updated: 2026-07-13

## Tools

- Tools it lists (6, about 2,031 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-10-04 22:24 UTC):
  - `get_human_services` (read-only): Fetch the Human For AI manifest: available services, operator profile (location, languages, working hours), response times, accepted and rejected task types,…
  - `submit_human_task` (writes): Submit a task for the human operator to perform in the real world. Returns a task_id immediately; the human reviews every task before accepting it (this is not…
  - `check_task_status` (read-only): Look up a submitted task by its task_id. Returns current status (submitted → accepted → delivered, or rejected), status history with timestamps,…
  - `message_human_operator` (writes): Send a free-form message to the human operator — questions, scoping, custom or recurring projects, anything that is not yet a ready-made task. reply_to is…
  - `check_message_thread` (read-only): Read the thread for a message you sent: the original text, every reply oldest-first, and whether the operator has answered. Needs the message_id and the…
  - `reply_in_message_thread` (writes): Add a follow-up to a thread you opened — answer a question the operator asked, add detail, correct yourself, or withdraw the request. Prefer this over sending…
- How its tools read to an agent (0 errors, 0 warnings, 1 note, about 2,031 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - note TC24 server: 6 of 6 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/humanforai.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming