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.
-
compliance-watchgithub.com/robertogfortes/compliance-watchupdated this year
Contract and invoice compliance auditor built with Claude API. Hybrid RAG, tool use, MCP server, prompt evaluation, extended thinking. Full pipeline — not a chatbot.
MIT ★ 2 -
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 -
MCP server + multi-agent orchestrator over FRED economic data: constrained tool contracts, a supervisor delegating to specialist agents, prompt-injection containment, a token-budget guardrail, and a CI-gated evaluation harness. Runs fully offline with no API key.
★ 1 -
Enterprise knowledge assistant with routed RAG, LangGraph workflows, MCP tools, verified delivery, evaluation, and API-driven HITL writes.
-
GenAI QA & Evaluation framework for RAG systems: API, Playwright UI, RAG evaluation, prompt-injection tests, a Python MCP server, and GitHub Actions CI
-
Cited-answer RAG service over 4 Czech labour laws: hybrid retrieval, LLM reranking, REST API (FastAPI) and MCP server for AI agents, offline evaluation with confidence intervals.
MIT -
Persistent memory and context-engineering platform for AI agents with memory intelligence, hybrid retrieval, token-budgeted context compilation, custom LLM APIs, MCP, evaluation, observability, and a React control plane.
-
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 -
An integrated AI platform composed from nine of these libraries: an authenticated multi-tenant API, OpenAI and Anthropic failover, streamed agent steps, an MCP server, per-tenant memory, durable multi-agent jobs with crash recovery, tracing, and evaluation.
MIT -
Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.
npm MIT ★ 171 -
Local-first, open-source platform for AI agents and business workflows with typed, calibrated decisions. Ready-to-run flows for finance, sales, IT and customer service; visual builder, human approvals, evaluations, RAG, MCP, REST API, SDK and CLI. One command on your own computer; Docker Compose for servers.
Apache-2.0 -
Tool Offer Agent by Kingan Logic: source-attributed API/MCP offer drafting, review, readiness and export. Public judging snapshot; optional buyer-authorized FAHCE evaluation.
NOASSERTION ★ 1 -
github-insight-mcpgithub.com/wjddusrb03/github-insight-mcpupdated this year
Stop opening 12 tabs to evaluate a library. GitHub repos + npm/PyPI packages + security advisories in one MCP tool call. Zero API keys required.
MIT -
pipeworx-mcp-mathjsupdated this year
MCP server for mathematical expression evaluation and unit conversion via mathjs API
npm MIT -
Enables LLMs to search and evaluate Steam games — prices, discounts, reviews and Steam Deck compatibility with no API key, plus a player's library, achievements and friends via the official Steam Web API.
npm MIT -
Source discovery and reuse prototype: pinned evidence, license notices, agent API, CLI and MCP. Controlled evaluations; independent usefulness remains unproven.
MIT ★ 1 -
Cortex-aigithub.com/CharonK652302/Cortex-aiupdated this year
Production RAG app — LangChain LCEL, LlamaIndex, Crew.ai multi-agent, FAISS, FastAPI, Docker, MLflow evaluation, GitHub Actions CI, MCP server — zero paid APIs
-
Python browser automation with Camoufox, session persistence and a 17-tool MCP server. CLI and Python API for authorized QA, accessibility and agent evaluation.
MIT ★ 3 -
RevRule by Payload as an MCP server: read entitlement graphs and payout evidence, and dry-run revenue events, via the Payload rail API. A free self-serve console key is enough to evaluate.
mcpb MIT -
loan-ai-assistantgithub.com/aishwarya14-dev/loan-ai-assistantupdated this year
This project extends the Loan Rule Engine with an AI Operations Assistant using MCP. It communicates with the Rule Engine over REST APIs and provides natural language access to rule evaluations, analytics, and audit information.
-
An MCP (Model Context Protocol) server that assesses open-source dependency risk — CVEs, license conflicts, maintenance health — for npm, PyPI, Cargo, Maven packages plus a 3-agent reviewer (Triage → Research → Synthesis) built on top of it that evaluates a PR's dependency changes end-to-end. Built on free, no-auth APIs: OSV.dev,deps.dev, github
★ 1 -
An MCP server for the PGS Catalog REST API — the EMBL-EBI catalog of published polygenic scores, their traits, publications, evaluation samples, and reported performance metrics.
Apache-2.0 ★ 1 -
MCP server for the PGS Catalog: published polygenic scores, the traits they predict, development/evaluation ancestry, per-score licences, performance metrics and source publications, via the official REST API.
MIT -
corellium-mcpgithub.com/H4RR1SON/corellium-mcpupdated this year
Code-mode Model Context Protocol (MCP) server for Corellium: the full 206-operation mobile-security API behind two tools, executed in a token-isolated V8 sandbox. Ships a token-efficiency A/B evaluator.
MIT ★ 2 -
A comprehensive Model Context Protocol (MCP) server providing real-time YouTube Data API access for AI assistants. Features 14 functions including intelligent content evaluation with technology freshness scoring for knowledge base curation.
pypi MIT ★ 13 -
Executable architecture governance. A CLI, MCP server and REST API that check a repository against Rego/OPA rules — and report a rule they could not evaluate as a failure, never a silent pass.
npm MIT ★ 2 -
Synapse_OS is an agent-first project operations platform for managing multi-agent workflows, structured tasks, handovers, memory, and evaluator-based quality scoring. It combines FastAPI, Next.js, PostgreSQL/Qdrant, MCP/agent-tool APIs, and OpenAI/Playwright UAT testing.
MIT ★ 1 -
Private, self-hosted AI platform that runs on one laptop (no cloud, no GPU, no API keys): agentic RAG with citations, LangGraph + MCP tools, LiteLLM routing with an evaluation gate, MLOps (Dagster, MLflow, BentoML), OpenTelemetry tracing, SSO and Argo CD GitOps on k3s with Ollama.
MIT ★ 9 -
Machship MCPno update data
# Machship MCP Server Connect your AI assistant to the Machship freight platform and manage shipping operations directly through natural language. Machship MCP enables AI agents to interact with freight workflows including consignments, quotes, carriers, labels, manifests, locations, and business entities. ## What you can do - 📦 **Consignments** — create, update, search, track, and manage shipments throughout their lifecycle - 💰 **Quotes** — retrieve carrier pricing, compare services, and evaluate transit options - 🏷️ **Labels & Manifests** — generate shipping labels, create manifests, and manage carrier bookings - 🚚 **Carriers & Services** — discover available carriers, routes, and delivery options - 📍 **Locations** — search, validate, and manage pickup and delivery addresses - 🏢 **Companies & Identities** — manage organisations, users, and account relationships - 📎 **Additional workflows** — handle attachments, invoices, custom schemas, and shipment consolidation ## Coverage **125 tools across 21 modules** providing broad access to the Machship API through a single MCP server. ## Compatible clients Works with any MCP-compatible client, including: Claude Desktop · Cursor · VS Code · Windsurf · Goose · Warp · LM Studio ## About Built by [Devkind](https://devkind.com.au) — delivering modern software solutions and AI-powered integrations for businesses worldwide.
smithery -
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 -
Testing AI-facing APIs: an own MCP server and an LLM endpoint on Claude with evals, groundedness and prompt-injection checks
MIT -
The SandboxAPIs MCP server: read-only, API-compatible replicas of 21 developer APIs, preloaded with one simulated company, for testing agents without a test account.
npm MIT -
Agent gateway for external tools — Rhumb Index scores services; Rhumb Resolve routes supported capability calls through governed execution rails.
npm MIT ★ 6 -
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.
npm MIT -
Which API API — pick the model/API for each task by testing on your own examples, with real billed cost, a fallback router, model-integrity checks and an MCP server
AGPL-3.0 -
Guarded CLI, TypeScript client, and MCP server for JustHandled x402 agent utilities
npm MIT ★ 1 -
Soulfield Lens MCP server (npm wrapper around lens-api)
npm MIT -
Does a computer-use agent do the job every time? Bellwether measures pass^k on legacy enterprise screens: snapshot-forked trials, ground-truth verifiers that must prove they can fail, seeded fault injection, and a compiler that turns solved traces into deterministic MCP tools. Runs offline, no API key.
Apache-2.0 -
Visual end-to-end map of API, gRPC and database contracts with system-design checks, breaking-change diffs and AI-coding-agent impact analytics. CLI, web UI and MCP server.
NOASSERTION -
Verifiable NL2SQL agent: self-hosted MCP server, 3-config A/B/C experiment, deterministic offline grading, re-run noise audit (DeepSeek + DuckDB)
MIT ★ 1 -
Multi-AI consensus tool: MCP server that queries multiple AI models (OpenAI, Claude, Gemini, custom APIs) in parallel, synthesizes responses for better accuracy, and reduces AI bias through ensemble decision-making
pypi MIT License -
Production-grade Rust math CLI — 11 core plus optional time/unit/FX domains, symbolic calculus, arbitrary precision, interactive REPL, batch mode, and HTTP + MCP server mode with microsecond caching
cargo NOASSERTION -
ai-eng-prepgithub.com/tp-coder/ai-eng-prepupdated this year
Hands-on AI-engineering repo: a Python RAG pipeline that grows into a model-decided agent — with retrieval & trajectory evals, an MCP server, and per-run cost/token/latency observability in Postgres. Public and runnable.
-
Agentic WhatsApp customer-service assistant (Python, Claude API, MCP server) with guardrails, human handoff and eval-gated releases. Planning pack.
★ 1 -
Governance-classifier eval harness on the Claude Messages API, with calibrated LLM-as-judge and an MCP server
MIT -
Visually grounded document Q&A with verifiable page citations. Hybrid retrieval, quote verification. CLI, API, MCP and PNG overlay Next.js UI.
Apache-2.0 -
The plug-and-play evals layer for LLM-based projects: library, learning center, check center, API, MCP server.
MIT ★ 1 -
Domain-pluggable LLM agent runtime with tool permissions, human approval, MCP server, and a repeatable eval harness. Local models (llama.cpp) and hosted APIs.
MIT -
house-of-wisdom-mcpgithub.com/ezzohamdan/house-of-wisdom-mcpupdated this year
House of Wisdom MCP — multi-model consultation council. Diverse AI model families investigate independently and return their own perspectives; the orchestrator weighs them. Inspired by the medieval Bayt al-Hikma.
pypi MIT License -
MCP server for Recruitee service for easy LLM evaluation
★ 3 -
ALPNAI tools for authorized AI agents: deterministic cost, latency and quality analysis, reproducible examples, API/MCP integration and report delivery.
NOASSERTION -
Measure AI executions from an agent or assistant: MCP server and local plugin for the NeoMundi measurement API, with response-contract validation
NOASSERTION -
MCP server for the Woodstitch API: paid human listeners judge your text-to-speech audio in blinded pairwise preference or human-vs-AI detection studies.
pypi MIT -
AI analyst agent (Gemini + MCP tools over SQLite) tested on 22,641 clothing reviews. Compares its judgments with an ML baseline on 200 held-out reviews, audits disagreements, fixes a silent wrong-question bug (2/5 to 5/5), documents governance and limits. Includes a no-setup replay site.
-
An agent that takes booking calls for a diagnostic clinic: finds the exam, holds a slot, and hands over to a person with a named reason. A hundred scored golden calls gate CI; a second reader asks a local model through Ollama, measured on the same calls; an MCP server exposes the clinic as tools. No model or API key needed to run it.
MIT -
MCP server for the Woodstitch API: paid human listeners judge your text-to-speech audio blind (pairwise preference or human-vs-AI detection). Not MOS.
pypi MIT -
kakeibogithub.com/siash1/kakeiboupdated this year
A personal finance agent built from scratch on the raw Gemini API: hand-written tool-calling loop, double-entry PostgreSQL ledger, context caching, MCP server, 46-task eval harness, prompt-injection suite.
MIT -
Evidence-grounded AI orchestration: a planner turns one goal into parallel LangGraph workflows, exposed as MCP tools. Every output item cites its source file and line. Runs with no API keys.
★ 1 -
AI-assisted Magic: The Gathering Commander deck builder: cited RAG over cards and rules, a bounded tool-calling agent with human approval, and evals that gate CI. API, CLI and MCP server.