Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations

While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code.

ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer.

the pain:

your agent screams out an endpoint that never existed it makes confident assumptions and you spend hours debugging false leads

the fix:

ask-human-mcp gives your agent an escape hatch. when it’s unsure, it calls ask_human(), writes a question into ask_human.md, and waits. you swap answer: PENDING for the real answer and it keeps going.

some features:

- zero config: pip install ask-human-mcp + one line in .cursor/mcp.json → boom, you’re live - cross-platform: works on macOS, Linux, and Windows—no extra servers or webhooks. - markdown Q\&A: agent calls await ask_human(), question lands in ask_human.md with answer: PENDING. you write the answer, agent picks back up - file locking & rotation: prevents corrupt files, limits pending questions, auto-rotates when ask_human.md hits ~50 MB

the quickstart

pip install ask-human-mcp ask-human-mcp --help

add to .cursor/mcp.json and restart: { "mcpServers": { "ask-human": { "command": "ask-human-mcp" } } }

now any call like:

answer = await ask_human( "which auth endpoint do we use?", "building login form in auth.js" )

creates:

### Q8c4f1e2a ts: 2025-01-15 14:30 q: which auth endpoint do we use? ctx: building login form in auth.js answer: PENDING

just replace answer: PENDING with the real endpoint (e.g., `POST /api/v2/auth/login`) and your agent continues.

link: