MeatSpace MCP server

MeatSpace

Human-in-the-loop service for AI agents. When an agent hits a subjective, high-stakes, or ambiguous decision, MeatSpace routes it to a human who picks one of 2–4 options and returns a structured result.

Live at meatspace.run

What it does

An agent posts a title, optional content (text, markdown, HTML, or an image), and 2–4 labeled choices. A human reviewer is shown the request, picks one, and the API returns the selected id and label. The agent waits via long-poll or webhook.

Typical use cases:

• Approval gates before destructive or irreversible actions (deploys, deletes, payments).
• Subjective tie-breaks where the model is below its confidence threshold.
• Tasteful judgment calls — copy choices, design preferences, ranking ties.
• Escalation when an agent has run out of deterministic checks.

Don't use it when the task is deterministic, automatically verifiable, or low-stakes and easily reversible.

Three integration methods

All three sit on the same backing API and accept the same Bearer token.

Zero-setup self-service flow

A new agent can fully onboard itself in three calls — no signup page, no approval queue, no human in the setup loop:

1. POST /api/keys with {"name": "your-agent", "email": "owner@example.com"} → returns an API key instantly. Rate-limited to 5 keys per email.
2. POST /api/requests with the Bearer token, your title, and choices → creates the review request.
3. GET /api/requests/{id}/wait → blocks until the human responds, or times out and returns pending with a reviewurl and pollurl.

The same flow is available over MCP: initialize → tools/list → provisionapikey → askhuman. The provisionapikey and getservice_status tools require no auth, so a fresh MCP client can connect without credentials and bootstrap itself.

REST quickstart

Provision a key:

curl -X POST https://meatspace.run/api/keys \
  -H "Content-Type: application/json" \
  -d '{"name": "my-agent", "email": "you@example.com"}'

The response includes api_key — shown once, save it. All subsequent calls use Authorization: Bearer .

Create a request:

curl -X POST https://meatspace.run/api/requests \
  -H "Authorization: Bearer $MEATSPACE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "my-agent",
    "title": "Ship v2.0 to production?",
    "content": "All tests pass. Staging looks good. 2 minor lint warnings.",
    "choices": [
      { "id": "ship", "label": "Ship it" },
      { "id": "wait", "label": "Wait for next cycle" }
    ],
    "confidence": 0.7,
    "consequence_of_wrong_choice": "Premature ship affects ~50k users"
  }'

Response:

{
  "success": true,
  "data": {
    "id": "uuid",
    "status": "pending",
    "review_url": "https://meatspace.run/review/uuid?token=opaque-review-token",
    "poll_url": "/api/requests/uuid",
    "expires_at": "2026-04-23T19:00:00.000Z"
  }
}

Long-poll for the result:

curl https://meatspace.run/api/requests/{id}/wait?timeout=25000 \
  -H "Authorization: Bearer $MEATSPACE_API_KEY"

Returns { status: "completed", selected, selectedlabel, respondedat } when the human responds, or 202 if still pending.

Optional fields on POST /api/requests: contenttype (text default, markdown, html, image), decisionreason, confidence (0–1), consequenceofwrongchoice, recommendedoption, callbackurl (must be HTTPS and host-allowlisted), metadata (passed through to the webhook), runid, traceid, timeoutseconds (default 3600, max 86400).

MCP

Shortened. The full README is on GitHub.