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.
toddamerrill
NameIntel is a remote MCP server that scores brand names across five dimensions in a single call: domain availability, USPTO trademark conflict screening, social handle availability across 12+ platforms, SEO keyword strength, and AI findability (GEO score — industry-first; measur
kewin1807
An awesome collection of Model Context Protocol (MCP) tools
arczhi
gopls-mcp: Accelerate Go Code Navigation with your LLM !
ironwheel
ynaoto
The world most simplest MCP server sample, maybe.
kristofferv98
MCP Server wrapper for TTS engines (Kokoro TTS and OpenAI TTS)
WonderLand33
A Model Context Protocol (MCP) server that provides onchain tools for LLMs, allowing them to interact with the Solana network.
worryzyy
提供对 [public-apis](https://github.com/public-apis/public-apis) 数据库的智能访问和管理功能。为开发者提供便捷的公共 API 发现、搜索和集成服务。通过标准化的 MCP 协议,您可以轻松地在各种 AI 助手和开发工具中集成丰富的公共 API 资源。
Chazzychouse
A MCP Server and Client developed from the quick start guide in their documentation
ctvidic
effytech
MCP server created for Freshservice, allowing AI models to interact with Freshservice modules
CDataSoftware
This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free [CData MCP Server for Apache Hadoop Hive (beta)](https://www.cdata.com/download/download.aspx?sku=FIZK-V&type=beta).
Noquarter6
Real-time contractor license verification across 45 US states. Verifies license status, expiration, and disciplinary history directly against state licensing board portals.
thinkAmi-sandbox
wildsonbbl
Model Context Protocol server for GNNePCSAFT tools
gediaogege
Obtaining information about sex education
hyen43
MCP 서버 학습을 위한 간단예제 실습
ratnesh-maurya
yuqiaohan95
MCP server for intelligent code context — 87%+ token savings, zero resource overhead.
obiwan90
EdgeDB MCP服务器项目
Streamline-TS
MCP Server for Flyder
HBarefoot
Engram is a production-ready memory system that gives AI agents persistent, searchable memory across conversations. Think of it as SQLite for agent state - simple, fast, and reliable.
spoonbobo
OTRS MCP server
kelvinzer0
DevDocsMCP is a command-line tool that allows you to search and read documentation directly from DevDocs.io. It operates purely online, fetching data as needed.
OverQuotaAI
manamurah
ManaMurah MCP Server
zseta
MCP-native workflow engine for your AI harness. Progi teaches your agent how you like to get things done. So you can do your best work without re-explaining your process or losing context between sessions.
alphagroup-ai
leandro-jm
MCP Server para pesquisar em um API externa de uma aplicação web
rohanrav
Screeny is a privacy-focused macOS MCP server enabling AI agents to capture screenshots of user-approved windows
Spa42
MCP server configuration for beauty1 project
ivanboring
Exposes a SSE MCP server as a rest endpoints for tools. Only for testing
zuojianghua
企业微信群通知机器人
Abdssamie
Curated lists of mcp servers to use with ai agents or claude desktop
eyezhouyu
walker-capital
Real-time US storm intelligence for roofing and restoration contractors. Scored opportunities, property targeting, canvass routing, and FEMA claim data from live NOAA/SPC feeds.
Anticom
sungithubid
url to markdown mcp server
connectwithprakash
Repository for my MCP servers
BE-DCE
MCP server for DCE (Better Execute) — connects AI agents to EOS execution data: Rocks, Scorecards, V/TO, Level 10 meetings, to-dos, and topics. 13 read/write tools. Works with Claude, Cursor, and other MCP clients.
caok
uh-joan
eagurin
A modern, scalable MCP server implementation with support for multiple AI providers, advanced monitoring, and robust conversation management.
ban5104
turn an idea into a plan custom node.js mcp server that runs locally
KYBvWHxW
High-performance Manchu-Chinese translation server implementing the Model Context Protocol (MCP)
junct-bot
Swap routing, pool data, and liquidity queries across all Uniswap-supported chains.
MCP-Mirror
Mirror of
Mestika
Unofficial Model Context Protocol server for the Spotler SendPro API, formerly known as FlowMailer.
la-rebelion
Build AI Agents MCP-based
kuldeepsingh99
Build your own mcp server with spring ai
kennyfong19931
Get ETA (Estimated Time of Arrival) for public transport in Hong Kong.
dusk-network
Catch spec drift before it catches you. Pituitary indexes your specs, docs, and decision records, then detects overlap,
Prashanth684
MCP server that runs skopeo
agentset-ai
faranahmadk
MCP Java Client/Server using Spring AI
AgiMaulana
manahiyo831
This is experimental MCP server for operating tinySA.
Escorza07
mayankthole
Dhan Trading MCP Server
gomessoaresemmanuel-cpu
Multi-platform content distribution + draft/repurpose/schedule
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.