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.
SergioKingOne
moises-paschoalick
MCP Server using Spring AI
vishalkarmalkar
A test repository created using the GitHub MCP server
Meerkats-Ai
smartlead-mcp-server typescript
hauntingsteps
mcp server which will dynamically define tools based on swagger
sunil-kumar-h
This MCP server translates the user query to a steam pipe query that could be run on downstream cloud to fetch information on resources
Artmann
Let Claude interact with your Unity projects.
cpage-pivotal
viduycheung
brad04-ai
A headless data transformation agent that converts between 52+ format pairs including JSON, CSV, XML, YAML, TOML, HTML, Markdown, PDF, Excel, DOCX, and aviation formats (METAR, TAF, NOTAM). Discovered by AI agents via MCP, Google A2A, and OpenAPI. First 100 requests free, then pa
AnthonyUtt
Basic MCP server for interacting with Vikunja to-do app
stilllovee
MCP server allows agents to break tasks down and execute them sequentially.
dadepo
A Model Context Protocol (MCP) server that provides LLMs with network information lookup tools through WHOIS and RIPE Database queries.
BirdInTheTree
Read+write MCP server for Zotero with full write support — create items, manage collections, find and merge duplicates, import BibTeX
cactusaurelius
A Model Context Protocol (MCP) server for YouTube video transcripts and search.
davidmosiah
Unofficial local-first MCP server for WHOOP — recovery, strain, sleep stages, HRV, RHR and workouts. Privacy modes (summary/structured/raw), SQLite cache and doctor CLI for setup. Works with Claude Desktop, Cursor, Windsurf, Hermes, OpenClaw and any MCP-compatible client. Install
jomejia23
rehmat123
sjanaX01
barvhaim
This server enables AI agents to access real-time stock market data, historical prices, financial statements, and market analysis.
mikeysrecipes
PARK-JUHWAN
Precision calculators for AI agents (medical, finance, engineering, tax, physics). Pay-per-call in USDC via x402 on Base. No API keys.
willsygao
tian1ll1
A demonstration server implementing the Model Context Protocol (MCP)
systeminit
chitta-behera
MCP Server Demo Implementation
tiagonpsilva
tomoro-ai
Extended the anthropic mcp tutorial to support openai and customGPT connection through http-bridge
pravinkpk30
y16ra
Asura7969
seemsindie
Changerawr
MCP Server for interacting with your Changerawr instance!
chuckwilliams37
MCP server with Docker, Redis, and TimescaleDB
billychl1
olgasafonova
edsonsousa
O Legalis MCP traz todo o fluxo de trabalho jurídico da sua area de trabalho. Advogados podem criar e gerenciar casos, gerar peças processuais profissionais seção por seção com IA, conduzir entrevistas guiadas de intake processual e monitorar o uso de cota — sem sair da conversa.
prateekch
biocross
An MCP (Model Context Protocol) server that lets AI agents control Mac monitors via DisplayBuddy — adjust brightness, contrast, volume, input source, apply presets, sync displays, and more.
MCP-Mirror
Mirror of
michaelwybraniec
rajnaveen344
An MCP server to build LSP
Ropz3
sujithadr
MCP server Implantation for RAG (GroundX API)
bsmi021
This project provides a central gateway to manage multiple MCP (Model Context Protocol) servers, preventing the need to configure and run duplicate server processes for each LLM client (like Cline, Cursor, etc.). Connect your LLM client to the single gateway-client endpoint provi
devalexandre
pdfgate
302ai
提供搜索/代码运行/计算器/网页解析/网页部署等基本功能。
TychiWallet
Give your AI agent a wallet it can actually use. Tychi MCP plugs into Cursor, Claude Desktop, OpenClaw, and any stdio MCP host — onboard, create, import, and switch wallets with fast direct tools, then balance checks, sends, and policy-gated payments through tyi_chat. Keys live e
ericmarkson
runpod
Manage your RunPod cloud resources directly through an MCP-compatible client. Create, list, update, start, stop, and delete pods, serverless endpoints, templates, network volumes, and container registry authentications with ease. Streamline your RunPod operations using natural la
slotix
Read-only MCP server for your databases. Lets AI assistants inspect schemas, preview data, run read-only SQL, and join across PostgreSQL, MySQL, files (CSV/JSONL/Parquet), and S3 - 26 read-only tools. SELECT-only by server-side filter: the AI can look and explain, never write.
vyahhi
MCP Server to search and access Hyperskill educational content
Gainium
Read and manage Gainium DCA/Combo/Grid bots, deals, balances, backtests, the crypto screener, and curated strategy presets via MCP.
adologyai
Perplexity for social. Ask anything about what's happening across social and get answers grounded in real ad and creative data, not guesses.
harshal-14
MCP server example practice
wang-junjian
claymore666
# debmatic-mcp
dlwjdtn535
uupt-mcp
UU跑腿核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的同城配送服务商。
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.