MCP server

CompletionKit Official

com.completionkit/evals

Checked 25 Oct 2026, 20:29 UTC · It answered and asked for a sign-in

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

Needs a sign-in or keyVerified publisher: completionkit.com

https://completionkit.com/mcp

At a glance

Type: MCP server
Publisher: completionkit.com (verified by the MCP Registry)
Status: Needs a sign-in or key
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 25 Oct 2026, 20:29 UTC

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http evals https://completionkit.com/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.evals]
url = "https://completionkit.com/mcp"

Gemini CLI

{"mcpServers":{"evals":{"httpUrl":"https://completionkit.com/mcp"}}}

Cursor

{"mcpServers":{"evals":{"url":"https://completionkit.com/mcp"}}}

VS Code

{"servers":{"evals":{"type":"http","url":"https://completionkit.com/mcp"}}}

Antigravity

agy mcp add evals https://completionkit.com/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"evals","server_url":"https://completionkit.com/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"evals","server_url":"https://completionkit.com/mcp"}

Needs a sign-in or an API key from its maker.

ZeroWidth Caliper
Build datasets and rubrics, then run evals that score your AI in Caliper.
Ai Eval
Cloudflare Workers MCP server: ai-eval
ContexteTech
Search and load AI datasets, prompts and few-shot contexts from the ContexteTech catalogue.
IA-QA — 130+ QA & Dev Tools for AI Agents
130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free.
Money Mind — the judge
Statistical adjudication for agents: backtest judges, fact-checks. Pay per call in USDC via x402.
AI PM Lab
Learn how AI products work: lessons, model cost comparisons, real experiments, PM guides.
Pqs
PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.
Claude Schema Output Agent
Claude Schema Output Agent

[![AptLynx](https://aptlynx.net/badge/com.completionkit/evals.svg)](https://aptlynx.net/servers/com.completionkit/evals)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents