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.
gusteycamargo
sanctifai
MCP-Reasoner
Model Context Protocol (MCP) server implementation using Google OR-Tools for constraint solving
Stock-Alpha
mondweep
This is a foundational code base to understand how to create remote mcp servers in cloudflare using the SPARC framework
forerunner2
这是一个查询天气的mcp server项目
gzfutureai
MokeGongWen is an AI-powered writing tool for government and corporate entities, supporting 15 state-mandated document types. Features format templates, compliance verification, contextual requirement analysis, and style optimization to ensure precise, regulation-aligned official
rpinedaMC
ks217
Simple MCP server to return current datetime
hightemp
A Model Context Protocol (MCP) server for integrating with SearXNG metasearch engine.
Pakvothe
Localization as code — 7 MCP tools to push, pull, translate, extract strings, and search translations. AI-powered, type-safe, 182 languages.
icip-cas
Please run `uv pip install pptagent` first
sjimnar
An AI agent powered by cline.bot designed to solve Capture The Flag (CTF) challenges on a Kali Linux virtual machine via an MCP Server.
stunt-double
Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do.
dmcsvoices
A simple chat loop that includes multple mcp servers.
akasharora963
shieldly-io
AI-Powered Security Analysis for AWS — official MCP server. Analyze IAM policies and CloudFormation templates from any MCP client.
sahil1115
Model Context Protocol for cassandra database
liqiongyu
# Xueqiu MCP
direct-web
MCP server for Drop Beacon — search EDC products, track drops, compare prices across 1,000+ brands. edc4me.com
authn8
MCP server for Authn8 2FA code access
AnyContext-ai
logly-uk
Logly MCP server
yujiosaka
A real-time HTML syncing server with hot reload capabilities, built using the Model Context Protocol (MCP)
Diegoescalonaro
Local-first, lightweight MCP server for per-agent key management.
kaeosdesign
awslabs
bocchiczennie
mthadley-workos
BrightLin
The most simple ModelContext Protocol server example, just say hello to user
darwintree
scottschreckengaust
Test bed for MCP Servers in a Mono Repo
MCP-Mirror
Mirror of
apifyforge
Data center site selection intelligence, delivered as an MCP server your AI agent can call directly.
PovedaAqui
Automated screenshot capture and document processing for MCP Clients
Laity624
sivakumarl
MCP Server with Cloudflare Workers
jonnyhoff
An MCP server to interact with SQLite databases
BitsBound
AI-powered contract analysis with partner-level redlines for Claude Desktop and Claude.ai. Features include contract processing with real OOXML Track Changes, clause extraction and analysis, risk scoring and favorability dashboards, negotiation email generation, and deal context
cdryampi
MCP de mi perfil
KauanIzidoro
mcp-server
benjaminr
MCP Server for Teenage Engineering EP-133 KO-II
ivan-mezentsev
This MCP server enhances LLM coordination, offering greater control and predictability, and significantly reduces billable requests by minimizing user interactions within a single task.
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 QuickBooks (beta)](https://www.cdata.com/download/download.aspx?sku=RQZK-V&type=beta).
mohemohe
MCP server for shikorism.net
Sk-Mahammad-Irfan
chinpeerapat
OpenAPI server for Smithery Registry, providing access to MCP servers
CaChiJ
서울시 교통 데이터 MCP 서버 - 실시간 교통 정보, 대중교통, 따릉이 등의 데이터를 제공하는 MCP 서버
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 Google Search (beta): https://www.cdata.com/download/download.aspx?sku=BLZK-V&type=beta
MCP-Mirror
Mirror of
taiji1985
A MCP Server Of python runner
pgpt-dev
MCP Server for Private GPT
qiangge2008
goalves
prototype MCP server around generating PNG from ZPL so that agents can iterate better on results when someone asks me to build a really complex ZPL label layout
nlxai
apifyforge
Product safety intelligence for any product, manufacturer, or category — pulled from CPSC, NHTSA, FDA, and CFPB databases and scored through four analytical models.
vincentvella
Drives a browser - or a native Expo/React Native app on iOS/Android - and your dev server, putting both on one correlated timeline so a browser console error and the backend stack trace from the same moment line up. For Claude Code and AI agents.
MCP-Mirror
Mirror of
deep-ai-kr
apifyforge
Open source supply chain risk analysis via MCP — give your AI agent direct access to CVE records, CISA KEV exploits, maintainer bus-factor scores, and typosquat detection across 7 live intelligence sources.
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.