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.
WindoC
This project provides a simple yet powerful OCR (Optical Character Recognition) service through a FastMCP server, leveraging the capabilities of the Google Gemini API. It allows you to extract text from images either by providing a file path or a base64 encoded string.
emmapoderoso
Browser extension to enable MCP in claude.ai
li195111
Diagnoses token waste in Claude Code sessions. Detects 6 types of statistical anomalies with severity scoring. Fully local — parses ~/.claude JSONL files into SQLite, nothing leaves your machine. Plugin-native: one command install, then just ask "cta".
eZhing
Business management platform controlled entirely through conversation. Describe your business and AI builds your complete system — tables, views, dashboards, reports, chatbot
Tencent-RTC
It exposes Tencent RTC SDK documentation and Tencent RTC API resources to LLM-based tools. This improves the ability of LLM AI Agent to understand and interact with the Tencent RT SDK and API.
Arpitmahajan123
This project creates an MCP server using Node.js and TypeScript to autonomously control a smart bulb via UDP communication. It integrates with AI interfaces like ChatGPT or Claude, enabling seamless, anonymous, and automated lighting control with color and brightness adjustments.
thomasblc
Search, score, and submit 11,000+ AI agent tools from the SkillsIndex directory. Access MCP servers, Claude skills, GPT actions with security scoring (0–5), GitHub freshness, and honest picks.
JBAgent
Claude integration with MCP server for Microsoft Graph API
agentcentral-to
agentcentral is a hosted MCP server for Amazon sellers that connects Claude, ChatGPT, and other AI clients to Amazon Ads, Seller Central, inventory, orders, catalog, rankings, finance, and fulfillment data.
leonas5555
jovanSAPFIONEER
Multi-agent orchestration MCP server with atomic shared blackboard, FSM governance, per-agent budget enforcement, and adapters for 12 AI frameworks including LangChain, AutoGen, CrewAI, and OpenAI Assistants.
sudhanbhandari0
A simple coming soon website for testing
landing-ai
MCP Server for Vision Agent Tools
luis1232023
Stdio Mcp Server 转为 RestFul,轻松部署与 Web 服务集成, mcp gateway
rtbui2012
QuentinCody
amurshak
An MCP server for the Congress.gov API that consolidates 91 operations into 6 comprehensive tools that can be used by any MCP client (i.e. Claude Desktop), or MCP-compatible AI agent, to query and reason about congressional data.
jarrodcoulter
An example MCP server with a couple nmap scans as tools.
surveymars
Official SurveyMars Model Context Protocol (MCP) server that enables interaction with SurveyMars APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to create, distribute, and analyze surveys.
dynstat
A working example of your own agents from the scratch and using it with the mcp servers from scratch
realcrabcut
Turn YouTube videos into short clips — from Claude, Cursor, or any AI assistant that supports MCP.
ktwome
학습 보조 웹 서비스
HYPD-AI
Enable AI agents such as Claude, Co-Pilot, Codex, and other compatible tools to create, manage, and optimize advertising campaigns on ChatGPT.
shakunvohradeltek
This is a MCP Server for Claude-Code to connect to you Microsoft SQL Server
NoGraveDev
myonathanlinkedin
This project automates email-based user registration for LLM apps using the Model Context Protocol (MCP). It acts as a simple backend that receives email addresses from users, registers them with an MCP-compatible LLM server, and returns the generated API key or access token.
sanjeetkumaritoutlook-user
harshal-14
MCP server example practice
Sumedh1599
Uses Claude or OpenAI API to convert prompt-mapped input into concrete MCP server components such as tools, resource templates, and prompt handlers.
westvegh
The first strength-training app Claude can actually write to. Tally's first-party remote MCP server gives Claude read access to your real workout history and write access to your training plan: talk through your program in conversation — exercises, sets, progressions — say "put i
thinkchainai
wootock
OpenAI-compatible proxy with PII scrubbing, audit logging, and model routing. Drop-in replacement — set OPENAI_BASE_URL to point to this server. Supports GPT-4o, Claude, Gemini, and Llama via single endpoint.
kristianedlund
hardcover-mcp connects your Hardcover library to AI assistants like Claude and Copilot. Search for books, update your reading status, manage lists, explore series — all through natural conversation instead of clicking through menus.
linhai0872
MCP server that connects AI agents (Claude Code, Cursor, Codex) to Dida365/TickTick. 40 tools for tasks, projects, tags, habits, folders, and search — manage everything through natural language.
kani3894
Python MCP server for Hevy fitness app. Log workouts with natural language, search exercises, manage routines. Features web interface, demo mode, and 22 MCP tools.
ugobe007
AI-powered BESS quoting & energy sales intelligence MCP server
RedCiprianPater
NWO.CAPITAL is a multi-domain MCP server exposing 201 tools across 30 categories behind one Render-hosted endpoint with on-chain identity on Base Mainnet. Tools span autonomous-agent infrastructure, humanoid robotics + ROS2 control, biometric identity (ECG-based, soul-bound NFTs)
shwetha-sundar
webdevtodayjason
A2AMCP is a Agent2Agent MCP communication Server taking the concept from Google's Agent2Agent Protocol (A2A)
vystartasv
14 native MCP tools for AI agent infrastructure — facts, pitfalls, skills, handoff protocols, trust scores, identity verification, SLA validation, compliance-as-code.
madtaco-dev
Verification & utility API for AI agents — MCP server. Sanctions screening, company & tax-ID validation, and more. madtaco.dev
chew-z
MCP (Model Control Protocol) server integrating with Google's Gemini API
back1ply
MCP server to expose Claude Code Skills to AI agents
appendixhealth
Appendix turns any AI health conversation into a board-certified physician's opinion — with a real prescription when clinically appropriate. Search medical literature and submit a clinical encounter for review, all from your agent.
huangxinping
A MCP (Model Context Protocol) server for fetching HuggingFace daily papers.
alexandephilia
A powerful MCP server that enhances Claude's capabilities by integrating DeepSeek R1's cutting-edge reasoning engine.
gmogmzGithub
A lightweight knowledge base assistant using MCP with LLM integration. Features a streamlined server-client architecture combining custom tools with a knowledge base, all accessible via SSE transport. Ideal for building simple AI-powered knowledge assistants.
clawsearch
Security-first search engine for AI agent skills. Discover safe MCP servers and Claude Code skills with Trust Score ratings, 10-language semantic search, author verification, and trending rankings.
futurebrowser
RaleighSF
Burnwatch detects every paid service in your project, tracks spend across 14 AI-native tools (Anthropic, OpenAI, Vercel, Supabase, Stripe, Scrapfly, Browserbase, and more), and exposes real-time cost data via MCP tools — so any LLM can factor budget into its recommendations. Four
IzarLabs
MCP Server para análisis de datos sobre dataset del Titanic
influqa
Secure credit-based email infrastructure for AI agents with hosted MCP access, API-key auth, inbox creation, sending, memory, recovery, and Solana USDC credit payments.
samarabdelhameed
gtdfg6wgg8-ui
Pay-per-call x402 data APIs for AI agents, exposed over MCP. Multi-source web search (Hacker News + GitHub + Stack Overflow + Wikipedia in one call), multi-chain on-chain reads (balance, gas, tx across Base/Ethereum/Optimism/Arbitrum/Polygon), token rug-check, live DEX data, and
yamaru-eu
Yamaru Hardware Probe gives Claude Desktop and other MCP clients real visibility into your machine. 10 expert tools: full hardware inventory, real-time performance & thermal monitoring, RAM pressure analysis, SMART storage health, antivirus impact diagnostics, and LLM compatibili
apifyforge
Agricultural commodity climate risk intelligence for AI agents via the Model Context Protocol. This MCP server gives any AI assistant — Claude, GPT-4, Cursor, or a custom agent — direct access to live weather stress analysis, pest emergence monitoring, trade concentration scoring
QuentinCody
bzsasson
Discover the power of the “CLGateway”, an the open-source Claude MCP Server Gateway (available on GitHub). Built for users of Claude Desktop, Claude API or Claude Code, this Python-based gateway smartly manages your MCP (Model Context Protocol) servers and dramatically slashes to
bystray
MCP server for the GONKA network: run cheap LLM inference through the server (free trial or your own key), get multi-model second opinions, and compare live prices — for any AI agent.
rectalogic
PydanticAI LLM chat with MCP server tools
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.