RedCrown · MCP Server

The RedCrown prove-loop, as tools for your agent.

Run your inputs across every model and config, and get back the cheapest one that clears your quality bar, with a shareable proof. This endpoint exposes that loop to Claude and other agents over the Model Context Protocol.

This is a machine endpoint, not a web app. Agents connect to it over MCP; the protocol lives at POST https://mcp.redcrown.ai/mcp and requires an OAuth login with your RedCrown account. The server is a stateless shim: it validates your token and forwards it to the RedCrown API, so it holds no secrets and all data stays scoped to your account. Looking for the product? Visit redcrown.ai.

The two tools most callers need

`prove_task`

One call. A plain-language task plus a few examples, and RedCrown runs every model and returns the cheapest that clears your bar, with a shareable proof link. Leave the expected output blank to rank against the model you use now.

`try_sample`

A zero-input demo on a public dataset. Returns a shareable proof link with no keys and no setup.

Fifteen more advanced tools drive the full loop (import results, scaffold and run experiments, live proxy capture, and the reviewer decision report).

Connect your agent

Claude (Desktop / claude.ai): open connector settings, add a custom connector, enter https://mcp.redcrown.ai, and approve the OAuth login.

Claude Code:

claude mcp add --transport http redcrown https://mcp.redcrown.ai

Cursor, Codex, and other mcp.json clients:

{
  "mcpServers": {
    "redcrown": { "type": "http", "url": "https://mcp.redcrown.ai" }
  }
}

Once connected, try: "Use RedCrown to prove the cheapest model for classifying these support tickets." The agent calls prove_task and returns a proof link.

redcrown.ai Source on GitHub OAuth metadata