Discover Awesome MCP Servers

coding-agent-mcp

Containerized MCP server for coding agents with tools for file editing, shell commands, process management, Git, browser automation, and project snapshots.

cnnfag

CNN's Fear & Greed index for the US stock market: current score and rating, the seven component indicators, and about a year of daily history. Go standard library only, no API key required.

LLM Evaluation Harness MCP Server

Evaluates RAG outputs on faithfulness, answer relevancy, and context precision using an LLM-as-a-Judge backend. Exposes tools for running evaluations, scoring individual samples, and checking thresholds, enabling CI gating and on-demand assessment via MCP.

openai-image-mcp

Exposes multiple image generation backends as independent MCP tools for generating images with configurable models and parameters.

Open Brewery DB MCP Server

Provides access to the Open Brewery DB API, allowing AI assistants to search for breweries and retrieve detailed information like location, type, and contact details. It enables interactive exploration of a global database containing over 40,000 breweries.

srefix-diagnosis

A toolkit of 256 MCP servers for SRE incident diagnosis with Claude. One agent per tech (Postgres, Kafka, Istio, Kubernetes, Prometheus, MongoDB, Redis, Cassandra, ...) with failure modes, key metrics, and runbooks baked in. Plus telemetry MCPs (PromQL/LogQL/Elasticsearch), SSH-via-bastion executor, and 33 discovery adapters across 9 clouds. Apache 2.0, runs locally. Reproducible 5/5 scenari

EVIDIQ Circuit MCP

Verifiable API proxy and circuit breaker guard for autonomous agents, offering TLS attestation, payload schema inspection, circuit breaker enforcement, webhook signature verification, and 0G-anchored receipt attestation.

Mercury Spec Ops MCP Server

Enables AI assistants to dynamically generate technology-specific prompts and modular templates for PRD, codebase analysis, and bug analysis through programmable tools, supporting 31 technology stacks and multiple analysis dimensions.

SQL MCP Server

Enables natural language and SQL querying across SQLite, MySQL, PostgreSQL, and MongoDB databases with support for bulk operations and schema inspection. It features a safety mechanism requiring explicit user confirmation for destructive actions like data modification and deletion.

pfc-mcp

MCP server that gives AI agents full access to ITASCA PFC - browse documentation, run simulations, capture plots, all through natural conversation. Built on the Model Context Protocol, pfc-mcp turns any MCP-compatible AI client (Claude Code, Codex CLI, Gemini CLI, OpenCode, toyoura-nagisa, etc.) into a PFC co-pilot that can look up commands, execute scripts, monitor long-running simulations.

Company MCP Server

Enables AI to interact with internal company systems through API integration, supporting data search, information updates, report generation, and system connectivity.

cargo-mcp

cargo-mcp

Swagger MCP

High-performance server for exploring Swagger/OpenAPI specifications with dynamic session management, lightning-fast endpoint search, and efficient caching. Enables AI assistants to discover, search, and generate code from REST APIs.

raptio-mcp

Enables MCP clients to monitor KegLand RAPT fermentation chambers and RaptPill hydrometers via the RAPT.io API, and to control temperature, PID settings, and profiles when mutating operations are explicitly enabled.

Greek Financial Regulation MCP

Query Greek financial regulation data — regulations, decisions, and requirements from HCMC and Bank of Greece — directly from MCP-compatible clients like Claude or Cursor.

@processon/mcp-server-processon-node

Generates ProcessOn mind maps from Markdown content. Provides tools to check API key validity and create mind maps.

bscs-mcp

Deterministic, no-LLM MCP server exposing six operations from the Behavioral State-Change Selling methodology manifest.

K-Data Gate MCP Server

Provides Korean market data (products, trends, stocks, real estate) in English JSON for AI agents, with 13 tools including search, trends, and stock analysis.

Remote MCP Server Authless

Enables deploying a remote MCP server on Cloudflare Workers without authentication, supporting custom tools and connectivity to Cloudflare AI Playground and Claude Desktop via mcp-remote proxy.

x402 MCP Server

An MCP server that provides DeFi data tools (crypto prices, whale concentration, funding rates) for AI agents via the x402 protocol.

Polarion MCP Server

Integrates with Siemens Polarion ALM to manage test cases, test runs, and results, with support for JUnit import and spreadsheet export.

@striderlabs/mcp-grubhub

Enables AI agents to autonomously order food from Grubhub, including searching restaurants, browsing menus, managing cart, placing orders, and tracking delivery.

ofaudio-mcp

An agent-first MCP server for generating and transforming audio (music, speech, sound effects) via ElevenLabs and Mureka, providing tools for transcription, voice cloning, and multi-speaker dialogue.

drawio-mcp-server

Enables AI agents to create, read, update, and delete Draw.io diagrams, allowing automated generation of architectural diagrams, flowcharts, and visual documentation.

@cyanheads/internet-archive-mcp-server

Search the Wayback Machine and IA library (40M+ items), fetch archived snapshots, retrieve item metadata and full text via MCP.

mcp_calculator

A stdio MCP server that gives LLMs a safe scientific calculator with infix math, complex numbers, matrices, statistics, unit conversions, and more via tools that return JSON.

McpR

Aqui está uma demonstração de um servidor MCP (Multiplayer Control Protocol) usando SignalR: **Título:** Demonstração de Servidor MCP com SignalR **Descrição:** Esta demonstração ilustra como construir um servidor MCP básico usando o SignalR para comunicação em tempo real entre o servidor e os clientes. O MCP é um protocolo usado para gerenciar e controlar jogos multiplayer, e o SignalR facilita a criação de aplicativos web interativos em tempo real. **Funcionalidades:** * **Conexão e Desconexão de Clientes:** Os clientes podem se conectar e desconectar do servidor. * **Broadcast de Mensagens:** O servidor pode enviar mensagens para todos os clientes conectados. * **Mensagens Privadas:** Os clientes podem enviar mensagens privadas uns para os outros através do servidor. * **Gerenciamento de Jogadores:** O servidor mantém uma lista de jogadores conectados e seus respectivos IDs. * **Comandos Básicos:** Implementação de alguns comandos básicos do MCP, como `/list` (lista os jogadores conectados) e `/whisper [jogador] [mensagem]` (envia uma mensagem privada). **Tecnologias Utilizadas:** * **C#:** Linguagem de programação para o servidor. * **ASP.NET Core:** Framework para construir o servidor web. * **SignalR:** Biblioteca para comunicação em tempo real. * **JavaScript:** Linguagem de programação para o cliente web. * **HTML/CSS:** Para a interface do cliente web. **Estrutura do Projeto:** O projeto consistirá em duas partes principais: 1. **Servidor (C# ASP.NET Core com SignalR):** * Um Hub SignalR que lida com a conexão, desconexão e comunicação dos clientes. * Lógica para gerenciar a lista de jogadores conectados. * Implementação dos comandos básicos do MCP. 2. **Cliente Web (HTML/CSS/JavaScript):** * Uma interface web para conectar ao servidor SignalR. * Campos para inserir mensagens e enviá-las ao servidor. * Uma área para exibir as mensagens recebidas do servidor. **Implementação (Exemplo Simplificado):** **Servidor (C#):** ```csharp using Microsoft.AspNetCore.SignalR; using System.Collections.Generic; using System.Threading.Tasks; public class MCCHub : Hub { private static readonly Dictionary<string, string> ConnectedPlayers = new Dictionary<string, string>(); public override async Task OnConnectedAsync() { string playerId = Context.ConnectionId; ConnectedPlayers.Add(playerId, playerId); // Usando ConnectionId como nome inicial await Clients.All.SendAsync("ReceiveMessage", "Servidor", $"{playerId} entrou no jogo."); await base.OnConnectedAsync(); } public override async Task OnDisconnectedAsync(Exception exception) { string playerId = Context.ConnectionId; ConnectedPlayers.Remove(playerId); await Clients.All.SendAsync("ReceiveMessage", "Servidor", $"{playerId} saiu do jogo."); await base.OnDisconnectedAsync(exception); } public async Task SendMessage(string user, string message) { // Lógica para processar comandos MCP if (message.StartsWith("/")) { await HandleCommand(user, message); } else { await Clients.All.SendAsync("ReceiveMessage", user, message); } } private async Task HandleCommand(string user, string message) { if (message.StartsWith("/list")) { string playerList = string.Join(", ", ConnectedPlayers.Keys); await Clients.Caller.SendAsync("ReceiveMessage", "Servidor", $"Jogadores conectados: {playerList}"); } else if (message.StartsWith("/whisper")) { string[] parts = message.Split(" "); if (parts.Length > 2) { string targetPlayer = parts[1]; string whisperMessage = string.Join(" ", parts.Skip(2)); // Encontrar o ConnectionId do jogador alvo string targetConnectionId = ConnectedPlayers.FirstOrDefault(x => x.Value == targetPlayer).Key; if (targetConnectionId != null) { await Clients.Client(targetConnectionId).SendAsync("ReceiveMessage", user, $"(Whisper) {whisperMessage}"); await Clients.Caller.SendAsync("ReceiveMessage", "Servidor", $"Mensagem enviada para {targetPlayer}."); } else { await Clients.Caller.SendAsync("ReceiveMessage", "Servidor", $"Jogador {targetPlayer} não encontrado."); } } else { await Clients.Caller.SendAsync("ReceiveMessage", "Servidor", "Uso: /whisper [jogador] [mensagem]"); } } else { await Clients.Caller.SendAsync("ReceiveMessage", "Servidor", "Comando desconhecido."); } } public async Task ChangeName(string newName) { string playerId = Context.ConnectionId; ConnectedPlayers[playerId] = newName; await Clients.All.SendAsync("ReceiveMessage", "Servidor", $"{playerId} mudou seu nome para {newName}."); } } ``` **Cliente Web (JavaScript):** ```javascript const connection = new signalR.HubConnectionBuilder() .withUrl("/mccHub") .build(); connection.on("ReceiveMessage", (user, message) => { const li = document.createElement("li"); li.textContent = `${user}: ${message}`; document.getElementById("messagesList").appendChild(li); }); connection.start().then(() => { console.log("Conectado ao servidor SignalR."); document.getElementById("sendButton").disabled = false; }).catch(err => console.error(err.toString())); document.getElementById("sendButton").addEventListener("click", event => { const user = document.getElementById("userInput").value; const message = document.getElementById("messageInput").value; connection.invoke("SendMessage", user, message).catch(err => console.error(err.toString())); event.preventDefault(); }); document.getElementById("changeNameButton").addEventListener("click", event => { const newName = document.getElementById("newNameInput").value; connection.invoke("ChangeName", newName).catch(err => console.error(err.toString())); event.preventDefault(); }); ``` **Considerações:** * Este é um exemplo simplificado e precisa de mais tratamento de erros, segurança e funcionalidades para ser um servidor MCP completo. * A lógica de gerenciamento de jogadores pode ser expandida para incluir informações adicionais, como pontuação, nível, etc. * Os comandos MCP podem ser estendidos para suportar mais funcionalidades do jogo. * A interface do cliente web pode ser aprimorada para fornecer uma melhor experiência do usuário. * A segurança deve ser considerada, especialmente ao lidar com informações sensíveis. **Próximos Passos:** 1. Crie um projeto ASP.NET Core Web API. 2. Instale o pacote NuGet `Microsoft.AspNetCore.SignalR.Core`. 3. Configure o SignalR no `Startup.cs`. 4. Crie o Hub SignalR (como o `MCCHub` acima). 5. Crie a interface do cliente web (HTML/CSS/JavaScript). 6. Implemente a lógica de conexão, envio e recebimento de mensagens no cliente web. 7. Teste e depure o aplicativo. Este exemplo fornece um ponto de partida para construir um servidor MCP usando SignalR. Você pode expandir e adaptar este código para atender às suas necessidades específicas. Lembre-se de considerar a segurança e o tratamento de erros ao desenvolver um aplicativo de produção.

App Store Connect MCP Server

A Model Context Protocol (MCP) server for Apple's App Store Connect API. Manage your iOS, macOS, tvOS, and visionOS apps directly from Claude, Cursor, or any MCP-compatible client.

pastorsimon1798/mcp-video

MCP for video editing through ffmpeg

macctl

macctl is an accessibility-first macOS desktop automation MCP server that lets AI clients see the screen, inspect app accessibility trees, control mouse/keyboard, manage windows, and run commands, all behind tiered permissions and audit logging.