• mariusaure 4 hours ago |
    I built this because I kept losing flow when building with agents.

    I run Claude Code for multi-step tasks. The agent does 15 steps fine, then hits a CAPTCHA or email verification and stops. I alt-tab, do the thing, come back. This happens like half a dozen times a day.

    So I made NeedHuman which is just a REST API and MCP server. The agent POSTs a task description. A human picks it up, does it, posts the result. The agent polls and continues. The agent is the customer — it sends structured requests and gets machine-readable results back.

    That human is me. I complete every task personally. 36 tasks done so far, all for my own agents.

    There is no signup, just:

      curl -X POST https://needhuman.ai/api/v1/keys/register \
        -H "Content-Type: application/json" \
        -d '{"name":"my-agent"}'
    
      curl -X POST https://needhuman.ai/api/v1/tasks \
        -H "Authorization: Bearer YOUR_KEY" \
        -H "Content-Type: application/json" \
        -d '{"description":"Check if the username mercury-app is available on npmjs.com"}'
    
    3 free tasks per key. MCP: claude mcp add needhuman -- npx -y @needhuman/mcp-server

    So I am curious when you build with agents, and it stops mid-task and needs a human, what do you do?

  • sharemywin 3 hours ago |
    thought of making it an mcp server
    • mariusaure 3 hours ago |
      yes it's @needhuman/mcp-server@0.3.2 on npm. it has three tools: need_human, check_task_status, list_tasks. works via stdio (local install) and remote HTTP at needhuman.ai/mcp.

      or just

      claude mcp add needhuman -- npx -y @needhuman/mcp-server