MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Scenario-driven framework for evaluating demographic bias in single- and multi-agent LLM workflows. Tracks bias across sequential stages, separates model non-determinism from systematic effects, and prevents agents inferring evaluation intent. REST API and MCP server.
MIT -
A lightweight, pure web search solution for large language models, supporting multi-engine aggregated search, deep reflection and result evaluation. A balanced approach between web search and deep research, providing a framework-free implementation and mcp server for easy developer integration.
Apache-2.0 ★ 2 -
Open source AI evaluation framework — LLM-as-judge + assertion-based evals for any AI app. CLI + MCP server.
npm Apache-2.0 -
MCP server version of the AI ROI Calculator — evaluates ROI of AI/LLM implementations using a 3-layer cost framework via Model Context Protocol
MIT ★ 1 -
BestTestergithub.com/nshportun/BestTesterupdated this year
Production-grade Playwright + TypeScript QA framework with AI-powered testing, LLM-as-Judge evaluation, MCP server, 7 CLI agents, security fuzzing, CI/CD pipelines, Jira sync, and Slack reporting — zero-config, plug-and-play.
Apache-2.0 ★ 11 -
MCP server for building reusable LLM skills. Create, store, search, and invoke code patterns with persistent state and artifact management. Augmentation of the CORE framework (Comprehension, Orchestration, Reasoning, Evaluation) for structured agentic workflows. Inspired by Anthropic's "Building Effective Agents" & "Code Execution with MCP".
MIT ★ 2 -
Test each claim in a thesis against a measurement and get MATCH, DRIFT or UNVERIFIABLE, with a sealed record anyone can recheck offline. No model in the verdict step.
pypi NOASSERTION ★ 3 -
MCP for MCPs — score artifacts against rubrics, explain failures and iterate until a defined quality threshold.
MIT -
Quorel is an MCP server that scores AI agent responses before they reach a user, a trust layer an agent calls mid-turn, not a dashboard someone checks after the fact.
NOASSERTION -
Guardrails for LLM answers. GroundLens checks an LLM answer against its sources without a model, decides PASS, REVIEW or FAIL under your policy, and keeps a signed record.
pypi Apache-2.0 ★ 8 -
GenAI QA & Evaluation framework for RAG systems: API, Playwright UI, RAG evaluation, prompt-injection tests, a Python MCP server, and GitHub Actions CI
-
Python framework + local Studio for reliable LLM workflows: typed files in your repo, pre-run checks, experiments and evals, MCP server for coding agents
pypi NOASSERTION ★ 4 -
Open-source platform connecting AI assistants to government open data — MCP server, curated civic MCP directory, and anti-hallucination framework for all 559 Socrata portals
npm MIT ★ 48 -
vstackgithub.com/valani9/vstackupdated this year
AI agents fail like junior teammates, looping on bad ideas, ignoring feedback, and escalating commitment. vstack ports 34 of the most-cited organizational-behavior frameworks so you can diagnose your agents the same way you'd diagnose your team.
pypi MIT ★ 1 -
Glass Box Framework — runtime constitutional verification for AI answers. Trust Cards with claim-level reasoning chains, formal ECS scoring, the 7-angle Glassbox Court red team, and deterministic audit logs. MCP-native.
pypi Apache-2.0 ★ 10 -
A coding agent built from scratch (no framework) that fixes failing tests in a locked-down Docker sandbox. Benchmark of validated bugs injected into toolz and boltons; structured tools beat bash-only 33% vs 8% (p=0.022) on local Qwen3-8B. Runs free on Ollama. MCP server included.
MIT