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.
-
DCP-AI bridge for the Model Context Protocol (MCP): signed receipts for tool calls, DCP tools and resources
npm Apache-2.0 -
Busymate AI for Claude: connector listing and plugin bundle for the Anthropic directory, with live-profile checks. The MCP server lives in busymate-ai-src.
MIT -
Self-hosted, always-fresh RAG pipeline over the Anthropic GitHub org — grounded, cited Q&A over docs + issues/PRs/comments, refreshed hourly and served to AI agents over an MCP server.
MIT ★ 1 -
Run Claude Code on any LLM: a Cloudflare Workers AI gateway and LLM proxy that speaks the Anthropic Messages API and routes to Workers AI, OpenAI, Gemini, DeepSeek or Anthropic, with a prompt-injection session guard, red-team harness and MCP server.
MIT -
CLI, MCP server, and Anthropic/OpenAI API-compatible interface for Perplexity AI.
pypi MIT -
MCP server for responsible AI education on campus — built on Anthropic's Model Context Protocol
npm MIT -
An MCP server that enhances user prompts using AI providers (Anthropic, OpenAI, OpenRouter, Gemini)
npm Apache-2.0 -
Strapi v5 plugin with AI chat and MCP server — powered by Vercel AI SDK and Anthropic Claude
npm MIT -
codereview-mcpgithub.com/lfylow/codereview-mcpupdated this year
AI-powered code review MCP server supporting Ollama, DeepSeek, OpenAI and Anthropic.
MIT -
Self-hosted orchestrator for AI-agent workflows defined in YAML. Single Rust binary; Anthropic, OpenAI-compatible, gRPC and MCP tools.
Apache-2.0 ★ 8 -
Computer use for AI agents — control your Mac with Anthropic or OpenAI. CLI + MCP server + REST API + Dashboard.
npm Apache-2.0 -
@hasna/computergithub.com/hasna/open-computerupdated this year
Open-source computer use for AI agents — control your Mac with Anthropic or OpenAI. CLI + MCP server + REST API + Dashboard.
npm Apache-2.0 -
ucwgithub.com/Dicoangelo/ucwupdated this year
Cross-platform AI session capture using Anthropic's MCP protocol. Captures events from Claude, ChatGPT, Gemini into a local store.
MIT ★ 1 -
Local Multi-Protocol AI Gateway (OpenAI / Anthropic / MCP / NotebookLM RAG) for Google Gemini & Gemini 4 Argon
MIT -
video-extract-agentsgithub.com/cibis/video-extract-agentsupdated this year
AI-powered video extraction platform - CrewAI agents, MCP/SSE tools, Claude (Anthropic), AWS Bedrock, Angular, Node.js, Python, FFmpeg, Azure Container Apps
MIT ★ 1 -
ai-books-mcp-servergithub.com/Tryboy869/ai-books-mcp-serverupdated this year
🚀 AI Books MCP Server - Extend LLM context 15-60× via gravitational memory | Official MCP server for Claude Code & Anthropic
npm MIT ★ 4 -
Staff-level AI code review assistant with customizable perspectives. CLI + MCP server for Claude Desktop. Multi-LLM support (OpenAI, Anthropic, Ollama).
MIT ★ 1 -
AI career impact ratings for 1,028 skills across 88 roles. Python SDK + MCP server + OpenAI/Anthropic adapters + CLI. Install from source.
MIT -
Draft captions, emails, and scripts with Anthropic Claude, OpenAI GPT, or Cloudflare Workers AI through a Node.js SDK, CLI, and MCP.
npm MIT -
Integrate Arduino-based robotics (using the NodeMCU ESP32 or Arduino Nano 368 board) with AI using the MCP (Model Context Protocol) framework from Claude Anthropic
MIT ★ 81 -
broker-mcpgithub.com/Abhishekvoid/broker-mcpupdated this year
Capability broker for AI agents on Anthropic's MCP: ephemeral, policy-scoped tokens minted per tool call instead of standing credentials. Policy-at-mint + append-only audit.
MIT -
Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.
MIT ★ 2 -
claude-design-mcpgithub.com/e-brokenc0de/claude-design-mcpupdated this year
Unofficial MCP server that drives Anthropic's Claude Design (claude.ai/design) — create, generate, iterate, and export design systems from agentic coding CLIs.
MIT -
Awareness-SDKgithub.com/edwin-hao-ai/Awareness-SDKupdated this year
Local-first AI agent memory — one command, 13+ IDEs, works offline. Persistent memory for Claude Code, Cursor, Windsurf, OpenClaw. Zero-code interceptors for OpenAI/Anthropic. Python & TypeScript SDKs.
npm Apache-2.0 ★ 10 -
zbxmcpgithub.com/Monzphere/zbxmcpupdated this year
Native Model Context Protocol (MCP) server for Zabbix with an embedded AI assistant. Auto-generates API tools from the installed Zabbix version, enforces RBAC, supports OpenAI/Anthropic/Gemini/Ollama.
MIT ★ 6 -
MCP server exposing a typed tool layer over the Duffel travel API — flight, stay and car-hire search for AI agents. TypeScript, official Anthropic MCP SDK. Search-only, no booking surface.
MIT -
MCP server providing 100+ AI agent skills from Anthropic, Vercel, Trail of Bits, Hugging Face & more. Works with Claude, GitHub Copilot, and any MCP client.
npm MIT ★ 28 -
clawvr-mcp-servergithub.com/Steffd415/clawvr-mcp-serverupdated this year
Open-source Anthropic MCP server for small-business AI workflows. Built for Claude for Small Business. 13+ verticals. MIT. https://clawvr.com
MIT -
mcp-ragchatgithub.com/gogabrielordonez/mcp-ragchatupdated this year
MCP server that adds RAG-powered AI chat to any website. One command from Claude Code. Local vector store, multi-provider LLM (OpenAI/Anthropic/Gemini). Zero cloud dependency.
npm ★ 2 -
Governed AI agent over FDA labels, ClinicalTrials.gov and Medicare: MCP tools, Agent Skills, verbatim-citation grader; 95% vs 20% baseline, replicated on Claude Code and the Anthropic API
MIT ★ 1 -
List the models each AI provider's API serves (OpenAI, Anthropic, Gemini, Mistral, xAI, DeepSeek, OpenRouter) and see what's new since the last run. Zero-dependency CLI, library and MCP server.
mcpb MIT -
claude-pr-coachgithub.com/sik247/claude-pr-coachupdated this year
Junior Dev Accelerator — AI-powered pre-PR code review that teaches, not just flags. Supports Anthropic Claude, Google Gemini, and OpenAI. Runs as MCP server inside Claude Code or standalone CLI.
MIT -
Local AI resume & cover-letter builder: paste a job URL, get a tailored, truthfulness-guarded resume in four templates (PDF/HTML/ATS). Use the Anthropic API, or bring your own agent via MCP.
MIT ★ 5 -
Finds OpenAI, Anthropic, Google, Mistral, xAI, Cohere, DeepSeek, Groq, Bedrock, Vertex AI and Azure model IDs in your code and warns before they are retired. CLI, GitHub Action and MCP server.
npm Elastic-2.0 -
jira-pilotgithub.com/Aarul5/jira-pilotupdated this year
AI-powered Jira CLI and MCP server for humans and agents manage issues, sprints, boards with interactive wizards, multi-provider AI (OpenAI/Gemini/Anthropic), and an 14-tool MCP server for AI assistants
npm ISC ★ 4 -
Read-only AI SRE for Kubernetes. Finds what's wrong, explains why with evidence, and reports to your terminal or Teams. Never changes the cluster. Bring your own model: Microsoft Foundry, OpenAI, Anthropic or Ollama.
pypi Apache-2.0 ★ 3 -
AI-powered SRE incident response agent using Claude (Anthropic) + MCP – auto-diagnoses Kafka lag, CrashLoopBackOff, and TLS expiry on live EKS clusters | 12 operational tools, approval-gated mutations, full audit log
-
Run AI models like Llama, Qwen, and Gemma on every computer you own, and manage them for everyone on your network. Local first, with OpenAI- and Anthropic-compatible APIs, people and roles, and MCP.
AGPL-3.0 ★ 5 -
verity-fact-checkergithub.com/arsalanqasim/verity-fact-checkerupdated this year
AI-powered Slack agent that fact-checks claims, YouTube videos, and news articles — returning a source-quality-weighted verdict (True / False / Misleading / Unverifiable) as a threaded reply. Built with Slack Bolt, Claude (Anthropic), and Brave Search MCP.
-
Leave/PTO management server for the Model Context Protocol — pure accrual domain (DDD, Clean Architecture) exposed to AI clients via the official Microsoft/Anthropic C# SDK; 253 tests incl. protocol-level integration
MIT -
Configure a ClickHouse MCP server with LibreChat. This is a digital analytical interface to make inference on data across multiple AI agents all at once. LibreChat is Open Source and this connection is configured for Anthropic and ClickHouse Cloud.
-
MCP server that lets AI agents (Muse, Grok, and other MCP clients) orchestrate Claude Code cloud sessions via the Claude Code CLI. Requires @anthropic-ai/claude-code installed and signed in (run `claude` once).
npm 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 -
Model Context Protocol server for hookwarden — exposes the scan_handler tool so AI coding agents (Claude Code, Cursor, Continue, Anthropic Agent SDK) can find webhook signature-verification bugs locally across JavaScript, TypeScript, Python, PHP, and Go.
npm Apache-2.0 -
Python CLI and library that splits a request across AI agents, runs the tasks on any model (Ollama, OpenAI-compatible, Anthropic), and keeps a hash-chained ledger you can verify and replay.
pypi NOASSERTION ★ 4 -
claude-mcp-2600netgithub.com/astrutt/claude-mcp-2600netupdated this year
A remote MCP (Model Context Protocol) server that connects Claude.ai users to **2600net IRC** (`irc.scuttled.net`). Each user gets a persistent, NickServ-registered IRC nick. Built on Anthropic's FastMCP framework with Streamable HTTP transport.
MIT -
MCP Server Semgrep is a [Model Context Protocol](https://modelcontextprotocol.io) compliant server that integrates the powerful Semgrep static analysis tool with AI assistants like Anthropic Claude. It enables advanced code analysis, security vulnerability detection, and code quality improvements directly through a conversational interface.
npm MIT ★ 29 -
id.wisperagithub.com/gecochief/id.wisperaupdated this year
Passport & visa system for AI agent credentials. Detect, classify, and govern API keys, tokens, and secrets across MCP, OpenAI, Anthropic, LangChain, and more. Encrypted vault, policy engine, audit trails, delegation chains. Drop-in MCP server replaces plaintext credential storage.
npm MIT ★ 4 -
lazychat-erpnextgithub.com/soumyasethy/lazychat-erpnextupdated this year
LazyChat — an AI assistant docked inside your ERPNext desk. Chat with your data, draft reports, stage edits (Apply-gated). Bring your own LLM: any OpenAI-compatible or Anthropic key, stays in your browser. Also ships an MCP server (101 permission-scoped tools).
MIT ★ 22 -
Multi-layer AI agent system for intelligent infrastructure management. Features AI Terraform code editor with BYOK (Bring Your Own Key), Model Context Protocol (MCP) server with 45+ tools, and self-deploying Kubernetes observability agents. Supports OpenAI, Anthropic, and Azure OpenAI.
★ 6 -
Local mirror of AI-dev-tool changelogs (Anthropic, Cursor, Aider, Continue, MCP SDKs, etc.) with hybrid FTS5 + sqlite-vec retrieval, MCP server, curated cross-product synergies, and a fine-tuned changelog→action synthesizer (cs-actions:v1).
npm MIT -
AI-citable Japanese public business intelligence — 6-source Authority Chain (gBizINFO + J-Grants + 国税庁 法人番号 + EDINET + e-Gov 法令 + 官公需情報ポータル) as Claude plugins + Kokai Data MCP server. Anthropic financial-services equivalent for Japan. Apache 2.0.
Apache-2.0 ★ 2 -
BYOK-first AI gateway in one Go binary: free-tier LLM providers behind local OpenAI/Anthropic/Gemini/Responses endpoints — smart routing, token compression, semantic cache, MCP & A2A, built-in chat dashboard & desktop app. | 单文件 Go 网关:聚合各家免费额度,本地统一多协议端点,智能路由·令牌压缩·语义缓存·MCP,自带双语对话控制台与桌面端。
Apache-2.0 -
Self-hosted AI coding agent on AWS: the Rust agent on Lambda, AWS CDK infra and installer behind CoderHelm. Jira ticket to pull request, PR review, fix failing CI, alerts to fixes, CVE fixes, MCP server. Claude via Amazon Bedrock or Anthropic.
NOASSERTION ★ 2 -
Self-hosted LLM gateway that turns flat-rate AI subscriptions (Claude Code Max, ChatGPT Plus, Codex, Copilot, M365, Gemini) into one OpenAI/Anthropic-compatible API. Unified subscription wallet, OAuth passthrough on /v1/responses, prompt-injection + PII defense, MCP server, semantic cache, time-travel replay.
Apache-2.0 ★ 15 -
See where your AI agent's tokens go and stop paying for the ones that do nothing. Local CLI, MCP server, hook and proxy for Claude Code, Claude Desktop, Cursor, Codex, Gemini CLI and Anthropic/OpenAI/Gemini API apps. No API key, no telemetry.
npm MIT ★ 3 -
Open-source AI coding workbench in Rust: desktop app (GUI) + terminal TUI. Multi-session agents, plan and goal modes, built-in terminal and browser, diff review and Git commits, MCP client and server, skills, knowledge base and long-term memory. Works with OpenAI, Anthropic, Gemini, DeepSeek and more.
MIT ★ 38 -
Find the external APIs and AI models your code calls that already have a shutdown date, with the file and line. Runs in the browser, in CI, and inside your coding agent over MCP. Open knowledge base of published deprecations from OpenAI, Anthropic, Google AI, Stripe, Shopify and more.
Apache-2.0 ★ 1 -
Ask about Borsa Istanbul (BIST) stocks in plain Turkish or English. A Spring AI agent REST API (OpenAI or Anthropic) turns the question into tool calls on a Spring Boot MCP server (findSymbol, getQuote, getHistory) backed by TradingView and Yahoo Finance, and returns a grounded answer with the delayed market data as JSON.
-
openclaw-upgrade-orchestrator-mcpgithub.com/temurkhan13/openclaw-upgrade-orchestrator-mcpupdated this year
MCP server for safe AI agent runtime upgrades — user-driven regression detection (catalog + pre/post snapshot diff + rollback) AND provider-side regression detection (passive fingerprint of latency/response-shape/model-version drift across hosted Anthropic/OpenAI/etc. calls). Read-only advisor: never executes the upgrade itself; operator retains full agency.
pypi MIT License