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.
-
GenPark Reasoning MCTS Step Verity Evaluator - Implements Monte Carlo Tree Search (MCTS) Step-Level Process Reward Modeling (PRM) & Hallucination Branch Pruning.
MIT -
Universal Model Context Protocol (MCP) server and CLI runner for TypeSafe Jev decision models. Calibrated evaluation for code reviews, acceptance gating, and agent guardrails across Claude Code, OMP, and Cursor.
MIT ★ 2 -
A Model Context Protocol server with machine learning engineering tools: BPE token counting and cost estimates, BM25 search, paired bootstrap and McNemar evaluation comparison, JSON Schema validation, and prompt-injection and PII scanning.
MIT -
Model Context Protocol (MCP) server for intelligent task management, evaluation scoring, and session-based workflow tracking. Seamlessly integrates with AI assistants to provide structured task orchestration, real-time progress monitoring, and comprehensi
npm MIT -
The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learning.
Apache-2.0 ★ 23 -
Self-hosted data annotation and labeling platform for images, video, audio, text, PDF and LLM evaluation. Your storage, your models, your cloud.
NOASSERTION -
Model Context Protocol (MCP) server for intelligent task management, evaluation scoring, and session-based workflow tracking. Seamlessly integrates with AI assistants to provide structured task orchestration, real-time progress monitoring, and comprehensive evaluation metrics.
MIT ★ 3 -
Anistroph - multi-domain predictive analytics architecture for temporal and non-temporal modeling, explainability, multidimensional evaluation, and MCP-based inference with Claude and AI agents.
GPL-3.0 -
Read-only MCP server for QlikView Desktop: script, data model, sheets & charts via static export parsing, plus live expression evaluation via COM (Windows only).
MIT -
MCP-native job search: deterministic sourcing + scoring, with Claude (the host model) as the job-fit evaluator. Inline review UI as an MCP App.
npm MIT -
Strategic BDI reasoning engine for autonomous AI agents — goal decomposition, utility scoring, risk evaluation, and reactive replanning over PuterVision memory and world models.
npm MIT -
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 -
t1-t2-protocolgithub.com/Fauxetine/t1-t2-protocolupdated this year
MCP server for heterogeneous AI validation — T1 structured reasoning, T2 cross-model evaluation, and deterministic checksum. Python stdlib-only.
Apache-2.0 -
A secure Model Context Protocol (MCP) server for mathematical expression evaluation with strict grammar validation.
-
MCP server that carries what one session learned into the next. A per-project ledger written as things happen, scored per task by TypeSafe's Jev evaluation model via the Vercel AI Gateway.
npm MIT -
A TypeScript implementation of a Model Context Protocol (MCP) server, designed to evaluate MCP capabilities over/with RAG (Retrieval-Augmented Generation)
★ 1 -
Universal code + logic calculator for AI models: execute 31 languages, evaluate logic, analyze complexity. Exposed via MCP.
pypi Apache-2.0 -
What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gateway.
MIT ★ 3 -
tuningengines-cligithub.com/cerebrixos-org/tuning-engines-cliupdated this year
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p
npm MIT -
Modular, observable RAG framework exposing tools via MCP (Model Context Protocol) — hybrid search, multimodal ingestion, evaluation, dashboard
MIT -
regex-toolkit-mcpgithub.com/vinkius-labs/regex-toolkit-mcpupdated this year
Vinkius Edge high-performance Model Context Protocol (MCP) server for evaluating and testing regular expressions.
★ 3 -
saigegithub.com/urmzd/saigeactive
Go SDK, CLI and MCP server for streaming agents, tools, memory, retrieval and evaluations, with pluggable model providers and durable execution.
Apache-2.0 ★ 6 -
jobopsgithub.com/HireBridge/jobopsupdated this year
A self-hosted Model Context Protocol server for the full job-search loop — portal scanning, JD evaluation, tailored resume + cover PDFs, outreach drafting, story bank, negotiation brief — all driven from your MCP-aware chat client (Claude Desktop, Cursor, any client that speaks streamable-HTTP MCP).
MIT ★ 1 -
mcp-rag-agentgithub.com/luisrodriguesphd/mcp-rag-agentupdated this year
This repository presents a production-ready RAG system combining LangGraph agent with Model Context Protocol (MCP) integration. Features hybrid search using Reciprocal Rank Fusion (RRF) via MongoDB vector and text searches, grounded responses using COSTAR prompting, and automated RAGAS-based evaluation for building reliable, context-aware AI agents
★ 4 -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
llm-chess-evaluation-harnessgithub.com/PythonicVarun/llm-chess-evaluation-harnessupdated this year
LLM Chess Evaluation Harness ♟️
MIT -
Pluralistic human evaluation infrastructure for AI in production
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 -
Model Finder: find the cheapest AI model that passes your own tests. MCP server + Agent Skills for model audits, evals, cheapest-first routing and local model sizing.
MIT ★ 7 -
One rubric, every decision model. Run the same typed questions on Jev, Clef and OpenAI's Decisions API, and see where they disagree on your own cases.
MIT -
Function-calling quality gate for MCP/agent tools: scan tools and skills, lint description boundaries, and score model tool selection. Local-first CLI + MCP server.
MIT -
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
npm MIT ★ 10 -
Local MCP server: find the cheapest AI model that passes your own tests
pypi MIT -
A local-first workbench for developing, inspecting, and benchmarking MCP servers against local (LM Studio, Ollama) or remote (OpenRouter) models — Web UI, CLI, and MCP interface over one shared store.
npm Apache-2.0 -
Self-hosted multi-agent AI platform: generates, evaluates and refines LLM answers until they hit a quality bar (~22% more accurate, ~45% fewer hallucinations)
MIT -
ML Referee evaluates whether candidate features add predictive value beyond a baseline for machine learning and forecasting. AI agents can preflight data, request quotes, and run authorized evaluations through MCP. Invite-only beta. Website: MCP endpoint: https://api.mlreferee.com/mcp
MIT -
—
npm MIT ★ 1 -
MCP server for mathematical expression evaluation with strict grammar validation
npm MIT -
A realistic fictional small business for testing AI agents: synthetic data generator, mock CRM/inbox/calendar/invoicing MCP servers, and verified workflow tasks.
Apache-2.0 -
promptup-plugingithub.com/gabikreal1/promptup-pluginupdated this year
AI coding skill evaluator for Claude Code — 11-dimension scoring, decision intelligence, PR reports
npm MIT -
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts with coding agents.
npm MIT -
MCP Server implementation of AgentFold - Long-Horizon Web Agents with Proactive Context Management. v2.0 adds analytics, validation, quality evaluation, and performance benchmarking.
npm MIT -
Multi-model fraud detector using Hugging Face + LangChain + MCP
Apache-2.0 -
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.
MIT ★ 1 -
Ask several LLMs the same question, have them grade each other blind, and measure how biased the graders are. A provider-agnostic LLM Council with judge-bias analytics, CLI, MCP server and web UI.
MIT -
🛡️ Analyze transactions for fraud using advanced models and tools, providing insights and risk scores to enhance investigation efficiency.
Apache-2.0 ★ 1 -
MCP server for the DecimalAI skills registry — skill search ranked by measured effectiveness
MIT ★ 1 -
Typed decision tools for AI agents, powered by TypeSafe Jev
MIT -
LLM planning agent over a forecasting backtest — strict tools, structured output, measured eval with failure analysis
-
Answers from authoritative public sources, with a citation for every number.
Apache-2.0 -
Behavioral safety, vulnerability probing, and product-risk auditing platform & MCP server for Generative AI & Large Language Models.
Apache-2.0 ★ 2 -
Behavioral safety, vulnerability probing, and product-risk auditing platform for Generative AI & Large Language Models.
pypi Apache-2.0 -
touchstone-mcpgithub.com/lluvr/touchstoneupdated this year
A cheap, deterministic first-pass filter for unsupported claims in LLM output, computed without a second model call. Not a standalone hallucination detector. MCP server plus the reference implementation of Touchstone Standard 1.0.
pypi Apache-2.0 -
A deterministic first-pass filter for unsupported claims in LLM output, computed without calling another LLM. Not a standalone hallucination detector. A spec plus reference implementation, shipped as touchstone-mcp.
Apache-2.0 -
Self-hosted panel gateway for LLMs: ask a collection of models at once, keep every answer side by side, rotate explorer models in, and let your verdicts pick the next panel. OpenAI, Anthropic, Gemini and Ollama APIs, an MCP server, Python stdlib.
npm MIT ★ 1 -
hlido-mcpgithub.com/ankitkapur1992-hlido/hlido-mcpupdated this year
Hlido MCP server — independent AI-agent trust scores, claim audits & comparisons over JSON-RPC. Live at hlido.eu/mcp
MIT -
MindRails Supervisor: Modellhinweise und Aufgabenprüfungen für Claude Code, Codex und MCP. Mit Plugins, lokaler App und Offline-Demo.
Apache-2.0 -
An inbox with judgment. MCP server that files every note, link and meeting line by itself: TypeSafe's Jev decides the kind, the project, the urgency and the duplicates, and your text is never rewritten.
MIT -
Connect AI coding tools to Seclai via Model Context Protocol (MCP) — manage agents, knowledge bases, and content sources from Claude, Cursor, Windsurf, and more
MIT ★ 1 -
ALPNAI tools for authorized AI agents: deterministic cost, latency and quality analysis, reproducible examples, API/MCP integration and report delivery.
NOASSERTION