What is an MCP server?
An MCP server is a program built on the Model Context Protocol that wraps a tool, data source, or API — like file access, a database, or web search — into a capability an AI assistant can discover and call.
Discover awesome MCP servers.
davidelavezzo114
AI powered Kubernetes Assistant
diplinfmarkodrews
Agent & MCP Server for the ReportServer using RPC interface
apifyforge
Government contract intelligence at your AI assistant's fingertips: this MCP server connects Claude, Cursor, Windsurf, and any MCP-compatible client to 9 federal data sources for live procurement research.
dynstat
A working example of your own agents from the scratch and using it with the mcp servers from scratch
OpenGerwin
mattmohandiss
AI-native CAD inspection, no CAD license required. CAD MCP Server bundles a WebAssembly Open CASCADE kernel so LLM tools can read, measure, and compare STEP files locally. The server returns measured facts; your AI assistant interprets engineering meaning.
vk0dev
Local-first Claude Code cost analyzer. Parses JSONL session logs to surface per-tool spend, daily trends, and optimization hints.
li195111
Diagnoses token waste in Claude Code sessions. Detects 6 types of statistical anomalies with severity scoring. Fully local — parses ~/.claude JSONL files into SQLite, nothing leaves your machine. Plugin-native: one command install, then just ask "cta".
true-alter
MCP server wrapping local Ollama models for Claude Code delegation
AgentModule
Agent Module serves structured, human-reviewed compliance guidance that agents consume at runtime — covering EU AI Act obligations, GDPR requirements, risk classification, prohibited practices, and transparency rules.
MCP-Mirror
Mirror of
AgentTools-Cloud
Discover agent-callable resources by intent — x402 paid services, MCP servers and A2A agents — via the agent-tools.cloud directory. 9 tools: search/get/list_categories (x402), search_mcp_servers/get_mcp_server, search_agents/get_agent, search_all, stats.
garyedgington
SchemaCheck Agent validates JSON payloads against JSON Schema Draft 7 and 2020-12 standards. Designed for agent-to-agent workflows, it returns structured validation results instantly — including field-level error paths, human-readable summaries, and optionally a corrected payload
bzsasson
Discover the power of the “CLGateway”, an the open-source Claude MCP Server Gateway (available on GitHub). Built for users of Claude Desktop, Claude API or Claude Code, this Python-based gateway smartly manages your MCP (Model Context Protocol) servers and dramatically slashes to
chin3
This project is a proof of concept for running a local-first multi-agent system using: 🤖 Local LLMs via Ollama 🧩 Simple function/tool-call detection using <tool_call>... 🔍 Brave Search API or optional Brave MCP plugin server 🧠 Two collaborating agents: Searcher and Synthesize
MasudOsmanmr9
an custom mcp server and custom mcp client project powered by ollama's llama 3.2
paracetamol951
Kash.click management assistant. Connect your assistant to your business complete sales history, clients, payments, tax information, employees, points of sales.
sena-labs
Run Warp Oz agents from any MCP client: Claude Code, Cursor, Codex, VS Code. Six tools over stdio or SSE, driving the documented oz CLI. Standalone, or embedded in the OzBridge VS Code extension. Requires Warp with the o
EdenYavin
MCP Server for using Garak LLM vulnerability scanner
aasherkamal216
A WhatsApp agent that uses WhatsApp MCP server to send messages and perform other actions.
rocksun
jspoelstra
Testing creation of simple MCP servers and integrating with LangChain agent
Sequenzy
Sequenzy MCP enables AI assistants like Claude to manage your email marketing directly. Add subscribers, create AI-generated email sequences, send campaigns, and track analytics—all through natural conversation. Perfect for SaaS founders who want to automate email workflows witho
mows21
MCP server for n8n integration with Claude and other LLMs
Spysailor
Implementation of OpenAI MCP Server
ausboss
A TypeScript example showcasing the integration of Ollama with the Model Context Protocol (MCP), specifically the Filesystem MCP Server. This project provides an interactive command-line interface for an AI agent that can utilize filesystem tools.
ry4ever
9 AI tools — sentiment, research, contract analysis, code review, data enrichment. Pay-per-call in USDC on Base via x402. No API keys, no subscriptions.
rifatcakir
AI-powered chat assistant for banking microservices using Spring AI and Model Context Protocol (MCP). Interact with your microservices through natural language chat, view accounts, personal details, and transactions—all in one unified interface.
marchampson
An mcp-openai-server for connecting via Claude or similar
rectalogic
PydanticAI LLM chat with MCP server tools
akiojin
www-zerotrusted-ai
A PII detection Agent which helps you detect PII entities in a given prompt.
rocnubie
davidmosiah
Agent-first local SEO scoring, search-intent and opportunity engine with CLI and optional MCP server.
cnoe-io
GitHub AI Agent powered by official GitHub MCP Server. Uses LangGraph and LangChain MCP Adapters. Agent is exposed on various agent transport protocols (AGNTCY Slim, Google A2A, MCP Server)
vtlk
exposes a remote MCP endpoint so agents can:
Fronesis-Labs
DCL Evaluator — cryptographic audit trail for AI agents. Powered by Leibniz Layer™
genomoncology
llm plugin of MCP for clients and servers.
JeanVittory
With this MCP, you can debug your application by querying any issue to an LLM using the latest documentation available on the web. We currently support LangChain, LlamaIndex, and OpenAI docs, but you can add any other sources as needed.
Agnuxo1
AES-256-GCM + Argon2id encrypted local vault for AI agent credentials. Store API keys, tokens, and passwords safely. Reference them as {{PLACEHOLDER}} in any AI workflow — LangChain, CrewAI, AutoGen, n8n, and 40+ frameworks.
boysoai
Claude Code MCP servers
garasegae
Agent-first skill marketplace MCP server. AI agents discover, install, and share reusable skills across 7 platforms (Claude, Cursor, Windsurf, Cline, VSCode, Copilot, OpenAI) via MCP protocol. 15 tools including skill search, download, upload, and agent discovery.
kk0811852-gif
GhostLex is a specialized Legal AI engine built for Indian litigation under the new BNS, BNSS & BSA frameworks. Plug it into Claude, Cursor, or ChatGPT and get exhaustive legal memorandums with Supreme Court precedents, old-to-new law mappings, and DPDP-compliant auto-formatting
richard-senior
A GO based MCP server for use with AmazonQ or any other MCP capable LLM Agent
CoinRithm
Let any AI agent paper-trade crypto spot, futures, and prediction markets on CoinRithm using a user-minted API key. A simulated 50,000 virtual-mUSD account (no real money, not financial advice), 21 scope-gated tools, and a public Agent Arena leaderboard. Works with Claude, ChatGP
Onplana
Connect Claude, ChatGPT, Cursor, Gemini, and GitHub Copilot to your Onplana project portfolio. List projects, track tasks, generate AI status reports, search across your workspace. OAuth + PAT auth, 27 tools, full audit trail.
falahgs
Mike25app
Control Facebook & Instagram Ads from Claude, ChatGPT, Cursor, or any MCP-compatible agent. Direct Meta Graph API v24.0 wrapper with 32 tools — no backend required, just bring your own Meta access token. Auto-batches bulk ops, pre-flight ads_volume checks, PBIA auto-provisioning,
aparajithn
Zen7-Labs
maroondlabs
Live codebase intelligence for AI agents. Analyzes import graphs (PageRank), git history (reverted commits, co-change coupling), and conventions to generate context files (CLAUDE.md, .cursorrules, copilot-instructions.md). Only surfaces non-discoverable information — things agent
ansis-m
adamkleingit
A Slackbot LLM agent that allows connecting to an LLM and MCP servers
WandererJack1
About An MCP server that autonomously evaluates web applications.
bneb
Wasm sandbox runtime for AI agent code execution. Executes JavaScript, regex, JMESPath, and SQL inside fuel-metered WebAssembly cartridges. Infinite loops trap in microseconds instead of hanging — deterministic failure for LLM-generated code.
gihanrangana
This Model Context Protocol (MCP) server brings the full power of the TanStack CLI directly into your AI assistant (Claude, Cursor, etc.). It enables your AI to search official documentation, discover libraries, fetch guides, and scaffold new projects—all without leaving the chat
Redtri-git
Connect your LLM to Amazon’s product catalog and display real-time results directly in chat. Easily browse, compare, and buy products — all inside your AI agent, chatbot, or tool.
LNDMN
🚀 MCP-Launchpad: Your one-stop hub for easily deployable MCP servers! 🐳 Dockerized & AI-agent ready. Launch powerful tools for your AI in minutes. ✨
n0mad-ai
Persistent memory for any AI assistant — Claude, ChatGPT, Cursor — backed by your local Obsidian vault. One daemon, all your tools.
davidmosiah
Common questions about MCP servers, tools, and integrations
An MCP server is a program built on the Model Context Protocol that wraps a tool, data source, or API — like file access, a database, or web search — into a capability an AI assistant can discover and call.
Every server's detail page includes ready-to-paste config snippets for Claude Desktop, Cursor, VS Code, and other common clients — most installs take just a couple of minutes.
Most servers listed here are free and open source. Some wrap third-party APIs (cloud services, paid data providers, etc.) that require your own API key or subscription.
A local MCP server runs on your device and usually connects over stdio, giving you more direct control over data but requiring a runtime and installation. A remote MCP server is hosted by a provider and connects over HTTP, making setup easier while adding network and provider availability dependencies.
Claude Desktop, Claude Code, Cursor, VS Code, Codex, and other AI clients that support the Model Context Protocol can connect to MCP servers. Configuration formats and supported transports vary by client.
Review the source repository, maintenance activity, dependencies, requested permissions, and data-handling documentation before installation, and prefer official or trusted maintainers. Use least-privilege credentials for sensitive access such as files, databases, shells, and production systems.