Loading…
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
CompletionKit is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 67/100. 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 CompletionKit to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
mcp add com.completionkit/evals https://completionkit.com/mcpReview the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-07-18T03:09:06.777199Z",
"publishedAt": "2026-07-18T03:09:06.777199Z",
"statusChangedAt": "2026-07-18T03:09:06.777199Z"
}
},
"server": {
"name": "com.completionkit/evals",
"title": "CompletionKit",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://completionkit.com/mcp",
"type": "streamable-http",
"headers": [
{
"name": "Authorization",
"isSecret": true,
"isRequired": true,
"description": "Your CompletionKit API token as: Bearer <token>. Create one under Settings > API tokens."
}
]
}
],
"version": "1.0.0",
"repository": {
"url": "https://github.com/homemade-software-inc/completion-kit",
"source": "github"
},
"websiteUrl": "https://completionkit.com",
"description": "Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge."
}
}