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.
-
MCP server providing tools for CrewAI Demo (see: kimwwk/crewai-demo)
-
A weather agent built with MCP Server created inside Gravitee and CrewAI for calling tools.
-
stonegategithub.com/thekeystoneproject/stonegateupdated this year
Universal MCP tool gateway for AI agent frameworks — compiled Rust server with adapters for Hermes, CrewAI, LangGraph, Haystack, OpenHands, MS Agent Framework, and Google ADK
NOASSERTION -
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 -
Project3-MCP-Infra-Operatorgithub.com/MozaarAI-Agentic/Project3-MCP-Infra-Operatorupdated this year
Autonomous Kubernetes remediation agent via MCP. 5 secured tools, 3-layer security (token auth + namespace sandbox + audit log), dual-transport stdio/HTTP, CrewAI + LangChain agnostic. Claude Desktop connected.
MIT -
novacorp-operations-assistantgithub.com/chiragsharma0794/novacorp-operations-assistantupdated this year
Multi-agent Operations Assistant built with FastMCP + CrewAI. An MCP server exposes tools over local documents and order records; a 3-agent crew (Researcher, Writer, Critic) searches, writes sourced reports, and self-checks every claim. Runs locally with Ollama. Week 14 mini-project — Futurense AI Clinic.
-
Turn a plain-English request ("compare Apple and Microsoft YTD") into a validated stock chart — a CrewAI multi-agent pipeline exposed as MCP tools for Claude Desktop/Code, using yfinance data, AST-validated code generation, and sandboxed execution. Runs on local (Ollama/DeepSeek-R1) or cloud (Groq, GPT-4o) LLMs.
MIT -
sota-mcpupdated this year
Model Context Protocol server for the SOTA marketplace — exposes register/sandbox/bid/deliver/payouts as MCP tools so autonomous agents (Claude Agent SDK, OpenClaw, LangGraph, OpenAI Agents SDK, Mastra, Pydantic AI, CrewAI, smolagents) can plug in without
npm MIT -
asoftimegithub.com/amatayomosley-web/asofupdated this year
Temporal-awareness hook for tool-using LLMs. Surfaces freshness verdicts on in-context data so stale information doesn't poison fresh reasoning. Adapters for Claude Code, Antigravity, generic harnesses (LangGraph, CrewAI, raw SDK pipelines), and an MCP server for any MCP-compatible client.
pypi MIT -
Web search, page reading and browser automation for Python and AI agents. Search Brave, DuckDuckGo, Yahoo, Mojeek, Google and Bing with no API key, read pages as clean Markdown, and give both to agents as OpenAI, Anthropic, LangChain, LlamaIndex or CrewAI tools, or over MCP. Browser TLS impersonation, consensus ranking, honest block detection, caching, Selenium and Playwright.
pypi MIT -
Python tool for extracting invoice, bank statement data and more.
-
hiveagent-mcpgithub.com/hiveagentiq/hiveagent-pythonupdated this year
Connect to HiveAgent — 586 MCP tools across 22 industry verticals. The Amazon for AI agents.
pypi MIT License -
Keyless x402 (USDC-on-Base) pay-per-call APIs for AI agents: maintained multi-ATS jobs & hiring feed, company/domain enrichment, email deliverability grading, Base-token honeypot/rug safety, and an MCP prompt-injection scanner (OWASP LLM01/LLM08, CI-gateable). Free previews, no API key. CLI / LangChain / CrewAI.
pypi MIT -
Multi-agent orchestration with memory, routing, and MCP tool integration
MIT -
forgemcpgithub.com/Dregen612/forgemcpupdated this year
Managed MCP infrastructure — give your AI agents production-ready tools
MIT -
outcome-enginegithub.com/joncaris/outcome-engineupdated this year
AI tools that only charge when they work. 11 Gemini-powered MCP tools. $0.10/success, failures free.
-
agentholdgithub.com/edobusy/agentholdupdated this year
Shared versioned state for multi-agent AI workflows. An MCP server.
pypi MIT ★ 2 -
Smith_Agentic_MCPgithub.com/AddisonTech/Smith_Agentic_MCPupdated this year
MCP server for Smith_Agentic - exposes crew runs as tools for Claude Code and Claude Desktop
MIT ★ 1 -
fablesgithub.com/Atum246/fablesupdated this year
📖 Build Flutter apps to APK, AAB & iOS — no Android Studio needed. 24 commands, 19 MCP tools, 26 AI agents supported.
MIT ★ 1 -
sigil-protocolgithub.com/sigil-eu/sigilupdated this year
SIGIL security layer for AI agent tool calls — scans MCP tool arguments for leaked secrets, enforces policies, and writes audit logs
pypi MIT -
x711github.com/criptic/x711updated this year
Universal pay-per-use tool API for AI agents — 23 tools, x402 USDC payments, Hive collective memory, Hallucination Pills, MCP server. Free tier 10/day, no signup.
pypi MIT -
Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
npm Apache-2.0 ★ 20 -
Agentic trading simulation with MCP market tools, AI trader agents, portfolio accounting and a trading dashboard.
-
New tools for your agent. No new accounts. One connection to a growing library of tools agents can pay for per call.
npm MIT ★ 5 -
x402-facilitator-proxygithub.com/seob5285-alt/x402-facilitator-proxyupdated this year
"An open, multi-tenant HTTP 402 infrastructure gateway and Model Context Protocol (MCP) server daemon built for autonomous AI agents. Enables programmatic 1% platform-fee split settlements in USDC on Base L2 with plug-and-play templates for Express.js, LangChain (TS), and CrewAI (Python)."
npm -
Ctrl+Z for AI coding agents: undo anything Claude Code, Codex, Gemini CLI or Cursor did — even rm -rf. Snapshots, bisect, MCP, Agent CI.
MIT ★ 4 -
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 -
Governed MCP server and agent runtime: signed action approvals, typed tool effects and audit logs for Claude Desktop, Cursor and custom agents.
pypi AGPL-3.0 -
MCP server that lets Claude query a GTM engineer agent's runs, costs, ICPs and prospect fit scores, plus one guarded action tool with preview, confirm and daily spend caps
MIT -
bubbleq-agentsgithub.com/Mikol838/bubbleq-agentsupdated this year
0-UI era. Official SDKs & MCP Server for Bubbleq - the machine-to-machine intelligence layer delivering zero-noise financial knowledge graphs to autonomous agents.
MIT -
The Postern runner inside every Sigrix bundle: serves one agent's describe, run, stream and status on loopback, checks the buyer's entitlement, and serves an MCP server's tools over the same four verbs.
pypi Apache-2.0 -
Open-source privacy testing for AI agents. Python SDK, CLI and MCP tools to detect data leaks across tool calls, memory, inter-agent messages and logs, with redacted reports and CI gates.
pypi MIT ★ 11 -
mcp-for-beginnersgithub.com/HamzahTariq11/mcp-for-beginnersupdated this year
An MCP server exposing five trip-planning tools — flights, hotels, weather, attractions and itinerary writing — driven by a Pydantic AI agent, with a FastAPI backend and chat UI. Built as a teaching example.
★ 2 -
Persistent memory for AI agents over MCP: knowledge graph, vectors and graph RAG on your own hardware. Install a node, connect Claude Code or another agent, use the seven memory tools.
pypi Apache-2.0 ★ 1 -
Flight recorder, MAST failure attribution & on-call ops loop for AI agents: replay, tamper-evident evidence, triage queue, letter grades, handoff briefs, fleet tail, price catalog, conversation recall. 53 MCP tools. Zero dependencies, Python 3.10+.
MIT ★ 1 -
A2A v1.0 multi-vendor agent exchange: JWS-signed Agent Cards with pinned vendor keys, deterministic trust and quarantine, cost- and reliability-aware broker over A2A, MCP tools, metered local LLMs, adversarial benchmark reported as n/N.
Apache-2.0 -
Polaxis-SDK-MCPgithub.com/nishant6118/Polaxis-SDK-MCPupdated this year
Python SDK and MCP server for Polaxis - AI agent governance platform. Evaluate every tool call against policies in real time: block dangerous actions, enforce budgets, route to human approvals. Under 5ms.
MIT ★ 3 -
vaylgithub.com/ac12644/vaylactive
Memory for AI agents where a wrong fact causes harm. When a medication or an account status changes, Vayl retires the old value, keeps the history, and double-checks risky changes before they apply. Open source, local-first, works with any MCP client or agent framework.
pypi Apache-2.0 ★ 3 -
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 670+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
AGPL-3.0 ★ 83 -
Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.
npm NOASSERTION ★ 15 -
FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-github.com/shoaib1522/FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-updated this year
XploitEye is a state-of-the-art, AI-powered multi-agent cybersecurity platform designed to automate the complete Cyber Kill Chain. By orchestrating advanced Large Language Models (LLMs) and industry-standard security tools, XploitEye provides a unified interface for both Red Team (Offensive) and Blue Team (Defensive) operations.