MeatSpace is a human-in-the-loop decision service that lets agents submit ambiguous or high-stakes choices for a human reviewer to select among 2–4 options and return the result. It supports REST, MCP over Streamable HTTP, and a browser SDK, plus long-polling or webhook delivery of the response.
From the registry: Human-in-the-loop for AI agents. Submit choices, get a human decision.
$ curl -X POST https://meatspace.run/api/keys -H "Content-Type: application/json" -d '{"name": "<your-agent-name>", "email": "<your-email>"}'Please install the `meatspace` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Obtain a MeatSpace API key** — Create a Bearer token by calling the self-service key provisioning endpoint. This is required for the ask_human tool; unauthenticated tools like get_service_status and provision_api_key can be used without it. Run: `curl -X POST https://meatspace.run/api/keys -H "Content-Type: application/json" -d '{"name": "<your-agent-name>", "email": "<your-email>"}'` (https://meatspace.run/api/keys'}],)
Canonical MCP server config (HTTP transport):
- url: `https://meatspace.run/api/mcp`
- headers:
- `Authorization`: `Bearer <your-api-key>`
Note: MeatSpace implements MCP over Streamable HTTP at the hosted endpoint. The Authorization header is required for ask_human, but get_service_status and provision_api_key are available without authentication.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.