com.completionkit/evalsai

CompletionKit

Verified · today

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

Install

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

Requires: Authorization

Our take

Runs prompt evaluations over MCP by applying a prompt to a dataset and scoring outputs with an LLM judge. It is aimed at prompt engineers, evaluation workflows, and teams iterating on AI quality without building their own eval harness. The use case is practical, but the project appears early and users should treat automated judging as useful signal rather than ground truth.

reviewed by hand · 2026-07-18

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
1
last commit
today
archived
no
license
NOASSERTION
in registry since
2026-07-18

github.com/homemade-software-inc/completion-kit

More in ai

browse all →
claude-flowai

claude-flow

Verified · 10 days ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed63k starschecked 10 days ago

tldrawai

tldraw

Verified · 11 days ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed49k starschecked 11 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 7 days ago

Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed30k stars5.2k dl/wkchecked 7 days ago

openmetadata-mcpai

OpenMetadata

Verified · 3 days ago

Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.

hand-reviewed14k starschecked 3 days ago

praisonaiai

PraisonAI

Verified · 7 days ago

AI Agents Framework with Self Reflection and MCP support

hand-reviewed8.4k starschecked 7 days ago

strataai

strata

Verified · today

MCP server for progressive tool usage at any scale (see https://klavis.ai)

hand-reviewed5.8k starschecked today