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.
Skitchy
Your AI forgets everything between sessions.
richbibby
A Python-based MCP (Model Context Protocol) server for Cisco Catalyst Center (formerly DNA Center) that provides tools for device management and monitoring.
mattcoatsworth
wojtyniak
chaso-pa
walti1972
mcp-cpp-project-indexer is a deterministic C++ source-range indexer for large, module-heavy projects and MCP-based AI code navigation.
arjunkmrm
MCP server for Singapore's Land Transport Authority (LTA) DataMall API
delexw
Gateway MCP Server - Routes tool calls to Docker-based MCP backends
twinic
configure mcp servers directly from prompt
dm0lz
Swiss Ephemeris MCP Server is a Model Context Protocol (MCP) server that provides precise astrological calculations—including natal charts, planetary transits, synastry, and solar return charts—using the Swiss Ephemeris. It exposes tools for LLMs and AI agents to retrieve planeta
nexbid-dev
Agentic commerce infrastructure for AI agents. MCP-native product discovery, contextual ad matching, and purchase facilitation with European privacy compliance (nDSG/GDPR).
derekalia
A Model Context Protocol (MCP) server for interacting with fal.ai models and services. Uses the latest streaming MCP support.
petercort
hauptsacheNet
Comprehensive reading capabilities for ClickUp
liuzhuogood
trezero
zazencodes
Production-ready MCP server that provides LLMs with essential random generation abilities, built entirely on Python's standard library.
chryaner
Let AI see, click, type, and fully operate virtual machines
AryaAkman
MCP Server to retrieve Formula 1 information (race, driver and car, etc.). Connects to Open Formula 1, which is an open-source API that provides real-time and historical Formula 1 data.
jherr
Super simple TanStack Start MCP server
Dragonscale-Labs
miyamo2
MCP(Model Context Protocol) server implementation. Just a toy.
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 IBM Informix (beta)](https://www.cdata.com/download/download.aspx?sku=JIZK-V&type=beta).
JackKuo666
A MCP Server for ChemRxiv
ElonJask
MCP server for Reqable local capture data
mymcp
A simple MCP server proxy service.
MCP-Mirror
Mirror of
EiceblueCloud
sagarnildass
MCP Crash Course: Complete Model Context Protocol in a Day course from Udemy
uptimerobot
UptimeRobot lets you monitor websites, APIs, servers, and services through natural conversation. Create and configure monitors of every type — HTTP, keyword, ping, port, heartbeat, DNS, API, and UDP — then pause, resume, retarget, or retag them as your infrastructure changes. Whe
ehmkz007
Egomessss
MCP-Mirror
Mirror of
mesh-hq
mcprepository
CLI tool to index MCP Servers to mcprepository.com
fugle-dev
olegshilin
MCP server for Eagle app
CharlieChenyuZhang
a repo to experiment with mcp client and server
ECEAthipanbose
MCP Server Demo repository for demonstration and development purposes.
MCP-Mirror
Mirror of
wangrzneu
carlosalvite
KosukeUchida
mcpを試す https://modelcontextprotocol.io/quickstart/server
WynnD
vdineshk
Behavioral trust scoring for MCP servers and AI agents. Live registry tracking 4,500+ servers with interaction history, success rates, and latency metrics to produce trust scores (0-100). Gate agent actions on real behavioral attestation data before executing sensitive operations
dusenkajozef
Subin-Vidhu
Trying out MCP Server
DenisPr97
sujaykundu777
Node express and React based MCP client server demo
mgaruccio
MCP server for handling large openapi specs
Sairammargam
lbdudc
The UVL Analyzer MCP is a Model Context Protocol (MCP) server designed to analyze feature models written in the Universal Variability Language (UVL). It provides a variety of tools to process and extract insights from feature models, such as identifying atomic sets, calculating a
Hades-gsl
MCP Server is a tool for injecting faults and performing stress tests on Kubernetes pods and hosts using Chaos Mesh.
gtiwari2015
Spring AI based MCP server demo
Ohanvi
spring-ai-mcp-server
aekanundatascience
MCP Server for Thailand Meteorological Department earthquake data - เซิร์ฟเวอร์ MCP สำหรับดึงข้อมูลแผ่นดินไหวจากกรมอุตุนิยมวิทยา
ryanemitchell
drewster99
Searches and scrapes the app store. Research apps, rankings, keywords, and dump detailed app metadata. Great if you want to compare other apps to your own. FYI, the project is also a CLI for macOS.
GuptaPurujit
MCP Server and Client for Nutritionix API v2
Akshay-Sisodia
Production-grade ModelContextProtocol (MCP) server for the Smallest AI Waves platform. Exposes all Waves TTS and voice cloning features as MCP tools and resources. Ready for deployment.
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.