Loading…
Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.
ML Referee is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 100/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding ML Referee to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
mcp add io.github.scarrico/mlreferee https://api.mlreferee.com/mcpReview the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-26T23:26:17.751876Z",
"publishedAt": "2026-10-26T23:26:17.751876Z",
"statusChangedAt": "2026-10-26T23:26:17.751876Z"
}
},
"server": {
"name": "io.github.scarrico/mlreferee",
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"access": "Invite-only beta with manual approval. Account, authorization and evaluation credits required. Paid purchasing is not live.",
"supportUrl": "https://mlreferee.com/support",
"versionNote": "The released v1.0 product uses the live MCP compatibility version 1.1.0. No unreleased v2 capabilities are included.",
"authentication": "OAuth through an approved client connection; compatibility is client-specific. Public discovery does not require sign-in.",
"productRelease": "1.0.0",
"documentationUrl": "https://mlreferee.com/agents",
"privacyPolicyUrl": "https://mlreferee.com/privacy",
"termsOfServiceUrl": "https://mlreferee.com/terms",
"integrationRepositoryUrl": "https://github.com/scarrico/mlreferee"
}
},
"title": "ML Referee",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://api.mlreferee.com/mcp",
"type": "streamable-http"
}
],
"version": "1.1.0",
"websiteUrl": "https://mlreferee.com",
"description": "Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta."
}
}