- Conduid
- Marketplace
- #eval
MCP servers tagged eval
14 live MCP servers tagged "eval", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with eval.
Skill Optimizer
Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs
Assay
An open, reproducible trust layer for AI artifacts — skills, MCP servers, agents, and plugins. Assay inspects code, runs sandboxed behavioral audits, and generates verifiable repo…
Swival
A small, powerful, open-source CLI coding agent that works with open models.
Evalmonkey
CLI for agent builders to benchmark & chaos test your AI Agents. Text, Voice, Code supported.
Agent Tool Forge
Production LLM agent sidecar + Claude Code skill library for building, testing, and running tool-calling agents.
Pickrate
Does an agent actually pick your MCP tools and Agent Skills correctly? Zero-config surface linting and selection evals.
Oncall Copilot
Provider-agnostic AI on-call assistant — RAG + a tool-using agent + an MCP server + an eval harness — runs on Claude, OpenAI or OpenRouter. A hands-on learning project.
Routeproof
Test how an AI host routes real user intents to your MCP server's tools — catch silent mis-routing before your users do.
Kaigo MCP
介護の需給データをAIエージェントの道具として公開するMCPサーバー。道具は3つ。呼ぶ側のモデルを変えても答えがぶれないよう、全国値を道具の応答に埋めた
Curate
Turn an OpenAPI/Swagger spec into a high-quality, curated MCP server — consolidates endpoints into clear tools and proves it with an eval harness.
Argon Agents
Argon adapters for AI agent frameworks: LangGraph checkpointer with whole-store fork, Mem0 sandbox factory, reproducible eval pins — versioned MongoDB sandboxes for agents
Ctxprofile
Offline CLI that costs an LLM request per context component and flags tool definitions you ship but never call.
Cherry Evals
Search, cherry-pick, and export examples from public AI evaluation datasets. Built for AI engineers and AI agents.
Eval
CI-embeddable eval harness for MCP agents — scores the sequence of tool calls your agent makes, not just text output