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.
Browse MCP servers by category and sort by GitHub stars or newest additions. Open a listing for configuration and setup details.
eversonl
A lightweight, command-line tool for managing Claude Desktop MCP (Model Context Protocol) configurations. This tool makes it easy to toggle MCP servers on and off, create preset configurations, and manage backups.
l10n.dev
Stop wasting AI tokens on localization. Instead of loading large i18n files into the AI's context, it translates them server-side via MCP (the ai-l10n-mcp package, built on the ai-l10n SDK), saving tokens and keeping the agent focused on coding.
DonaldTrump-coder
Using MCP Server on Claude for Desktop
LeadBroaf
Open-source, modular “brain” for AI employees. Integrates with n8n and workflow engines, features persistent agent memory, natural language interface, and feedback loops. SaaS-ready, extensible, and easy to deploy with Docker.
Million19
The llm_to_mcp_integration_engine is a communication layer designed to enhance the reliability of interactions between LLMs and tools (like MCP servers or functions).
GRID-is
An MCP server for using GRID API directly from Claude for Desktop
K1vin1906
MCP server for Claude Code — parallel multi-model queries, smart routing, image/video gen across OpenAI (GPT-5, GPT Image), Gemini (Imagen 4, Veo), DeepSeek, Kimi & 12+ providers
ehallmark
Python SDK and CLI for building decentralized agentic applications on the Nostr and Lightning protocols.
29decibel
a MCP server to record Claude conversation to markdown or Apple Notes
shivman
This project demonstrates an Agentic AI system that uses a Gemini-powered MCP server to interpret natural language instructions and automate Microsoft Paint using GUI simulation tools on Windows.
arkCyber
A powerful Rust-based chatbot MCP framework with multi-server support and tool integration capabilities.
agardnerIT
Deep-Identity-Inc
AI-powered identity verification for the agentic ecosystem.
Nirsisr
WhatsApp MCP Assistant (Client-Server)
Ddhjx-code
AI agent面试skill,可以模拟面试过程
AutomateLab-tech
Whole-site AEO/GEO audit. Point it at a site, get a ready-to-run plan your agent executes. Orchestrates the ai-seo + citation-intelligence MCPs.
shayne007
AI Agent MCP Servers Provide Tools For ai-agent-workflow of FinTech Project
JinsonWu
MCP server for ollama, openai, and anthropic bridging
Medhovarsh
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
nodlab
MCP server for productive development
IQAIcom
MCP server for IQAI's Agent Tokenization Platform.
kira1228
AI-powered Chat System with multiple MCP servers.
lucky-aeon
agent mcp server 社区
zzqfsy
openai agents chat demo. integration custom llm and mcp server and function tool
jasonmeverett
MCP Server for driving Cloudera AI's Agent Studio
Ayyappa054
A practical demonstration of integrating LangChain with Model Control Protocol (MCP) featuring both single and multi-server implementations. Includes examples of mathematical computations and weather queries using async operations, React agents, and OpenAI integration. Perfect fo
kristofferv98
Mcp server with singular tool communication to agent using o4-mini with OpenAI Agent SDK integration to manage google/apple calendar.
ntrtd
.NET Core D365 MCP Server exposing Dynamics 365 tools. Uses .NET OData client.
AI-Agent-Hub
OpenSource MCP Marketplace | MCP Servers Tools Meta Dataset | Web API | Web Client Integration
davidmosiah
Agent-first TikTok Content Posting API CLI and MCP server with dry-run publishing
francoisjosephlacroix
A rubber duck MCP server for your LLM coding agent
bsmi021
kira1228
AI-powered Chat System with multiple MCP servers.
aliceappai
Connect voice recordings and transcripts to AI clients for natural language querying, insights, and workflow automation.
ai-zerolab
MCP Server for openai image generation
Wolfe-Jam
Persistent Project Context for Google Gemini — IANA-registered .faf format · MCP server + Cloud Run REST API
Rybens92
moises-paschoalick
Este projeto é um playground para criar o primeiro servidor MCP (Model Context Protocol), um protocolo que permite integrar LLMs a recursos externos de forma padronizada.
AKzar1el
OAuth-protected Google Search Console analytics, URL inspection, sitemap, and indexing tools for MCP clients.
ahmedhassan456
Saqr-MCP is a powerful Python application that implements the Model Context Protocol (MCP) to enable advanced AI assistant capabilities. It supports both local models through Ollama and cloud models through Groq, providing a flexible client-server architecture
adeniyii
test chatbot using mastra's mcp docs server
njcx
本项目实现了一个兼容 OpenAI API 格式的 MCP-Client服务,允许通过标准的 OpenAI API 接口与本地 MCP-Server进行交互。
njcx
本项目实现了一个兼容 OpenAI API 格式的 MCP-Client服务,允许通过标准的 OpenAI API 接口与本地 MCP-Server进行交互。
godstale
Ollama MCP Chat is a desktop chatbot application that integrates Ollama's local LLM models with MCP (Model Context Protocol) servers
jghiglia2380
Persistent memory API for AI agents — works with Anthropic, OpenAI, Gemini, and any AI framework
drapon
wahidpanda
Using Multiple MCP server I am gonna making a AI AGENT BOT for personalized assistant. Stay Tuned
Ginga1402
Demo of implementation of MCP using Langchain MCP Adapters and Ollama
rwnalds
Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.
thealxlabs
AI integration hub — 25 plugins, 146 tools. Connect Claude, GPT-4o, Gemini & Ollama to Gmail, Spotify, GitHub Actions, Vercel, n8n, Notion and more. One installer. MCP + Telegram.
sibbl
A MCP Perplexity API server written in Typescript with stdio and SSE transport support.
FastAlertNow
to-aoki
This is an LLM application with chat functionality, featuring chat using RAG, a database, and MCP server capabilities. The UI is designed for Japanese users.
falahgs
oaslananka
AI-native TypeScript runtime and tools for A2A agent orchestration, MCP integration, registry, protocol, and CLI.
Bufigol
🚀 MCP Server: Platform enabling AIs to act as autonomous developers. From idea conception to final testing, automating the entire software development process. #AutonomousDev #AI #Innovation #SoftwareEngineering #FutureOfDev
ryaker
Command Execution MCP Server for Claude Desktop
agent-cards
MCP server for Agent Cards — prepaid virtual Visa cards for AI agents
HrRodan
A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.
xenarch-ai
x402 MCP server for AI agent payments. Gasless USDC micropayments on Base L2. Claude, Cursor, LangChain, CrewAI, AutoGen, LangGraph resolve HTTP 402 with no API keys. Non-custodial, settlement-provider-agnostic, 0% fee.
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.