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.
bivex
A comprehensive MCP server for Kanboard project management that provides tools for managing projects, tasks, users, comments, files, and more through the Kanboard API.
MLT-OSS
🎯FirstData MCP
patsnap
PatSnap Patent Briefing MCP is a Model Context Protocol server that connects AI agents to PatSnap's Patent Briefing capabilities. A quick-read tool for understanding a patent or patent family. It brings together bibliographic data, legal status, family information, the three core
CodeMill-Solutions
alexcc4
A lightweight MCP server for MySQL, built with python
GoPlausible
Vestige MCP Server implementation, Algorand batteries included!
pduggusa
genomoncology
llm plugin of MCP for clients and servers.
renyumeng1
xon-lang
tambo-labs
Buildy is a home for all the apps your agent builds you.
nadavkav
MCP server for teachers accessing PETEL
kshetra-studio
manolaz
rperezll
Laboratorio personal con MCP en TypeScript: MCP Server, MCP Client, Claude Desktop y OpenAI API
spencerhhubert
mcp server to run scripts on adobe illustrator
gopalcnepal
A Model Context Protocol (MCP) server for interacting with WordPress sites. This server provides tools to fetch posts, pages, categories, and site information from any WordPress installation with REST API enabled.
inomata137
Simple MCP server implemented in Rust
MCP-Mirror
Mirror of
shahriarb
Local Kanban MCP server
radu103
x51xxx
Advanced color operations MCP server with Material Design 3 support, CSS theme matching, image color extraction, and accessibility compliance. Features HCT color space for perceptually accurate operations.
MCP-Mirror
Mirror of
MCP-Mirror
Mirror of
flatirontek
Vybit is a push notification service that uses personalized sounds that you record or choose from thousands of searchable sounds. The information is in the sound!
munakata-hisashi
0xshariq
GitHub MCP Server
jhacksman
Comprehensive notes for Graph Databases and MCP Servers in order to have enough context from a LM to quickly get up to speed on Graph DB projects.
yunfanye
AI Friendly MCP Server for Hacker News
v-3
Discord MCP Server for Claude Integration
Obidel
MCP-native memory layer for Claude Code, Cursor, Cline, Continue, and 16 other AI tools. Hybrid search (BM25 + pgvector + graph), self-hosted on Supabase + Vercel, 100% MIT, no paywall.
jbw1991
guptaprakhariitr
MCP server for indic-normalize-mcp — see README
megmogmog1965
Example code for Anthropic MCP server.
edwardchoh
MCP server that exposes the Apollo.io API functionalities as tools
fiatgrowth
An MCP server for AI agents that provides access to curated financial product data. Search, compare, and get personalized recommendations across savings accounts, credit cards, personal loans, budgeting apps, and earning products. 21 tools, 54+ products across 11 categories. Buil
apimatic
rachelsu-blip
Ratnaditya-J
Audit-grade runtime that gives AI agents auditable, signed provenance — every tool call, evidence item, and decision traced end-to-end.
Kimkeunwoo-OSE
AI 기반 여성 의류 쇼핑몰 콘텐츠 자동화 시스템
bamwor-dev
MCP server connecting AI agents (Claude, Cursor, Windsurf) to real geographic data: 261 countries, 5.2M cities, rankings, comparisons, and 9 Bamwor indices. Free tier, no API key required. Powered by Bamwor.
cycle-sync-ai
This tutorial walks you through setting up a basic MCP (Model Context Protocol) server to expose read-only resources to Large Language Models (LLMs) like Claude.
zjf2671
arpit-patel1
hongsw
bsmi021
This template helps you quickly bootstrap a new Model Context Protocol (MCP) server project based on recommended practices.
marvinjude
taiji1985
A MCP Server Of python runner
rocnubie
Best AI Photo Editor (bestaiphotoeditor.app) is a browser-based photo editing and image generation platform that brings together more than 40 AI models under one roof. Users can remove backgrounds, swap faces, enhance resolution, generate images from text prompts, and even produc
mokemoke0821
Claude MCP Server Integration & GitHub Actions
alphaonedev
Persistent memory for any AI assistant. Zero token cost until recall. Stores memories locally in SQLite, ranks by 6-factor scoring, returns results in TOON compact format (79% smaller than JSON). 17 MCP tools, 20 HTTP endpoints, 25 CLI commands. 4 tiers from keyword to autonomous
DarkAngel22544
Razorpay's Official MCP Server
xhiroga
Your AI-assisted mentor for Blender.
MASAKASUNO1
mcp server for use when you want to make images casually. fal.ai and a very cheap hall of fame is also possible!
Johnnybar
lucianotonet
chiefnamingofficer
Learning what it means to use MCP by trying to interact with Dynatrace MCP server.
railsblueprint
texra-ai
caiyunapp
An Official Model Context Protocol (MCP) server for Caiyun Weather. 彩云天气官方 MCP Server
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.