Discover Awesome MCP Servers

Redfish MCP Server

Enables AI agents and LLMs to control and monitor Redfish-enabled hardware through power operations, system inventory, event logs, health monitoring, sensor readings, and user account management.

DevUtils MCP Server

Provides essential developer tools for workspace management, including advanced file searching, project structure analysis, and batch code editing. It enables users to efficiently navigate, analyze, and modify source code within their development environment.

McpLLMServer

A FastAPI-based MCP server that enables LLM agents to interact with Ollama models through standardized MCP tools, with optional MySQL and Redis integration for data persistence and caching.

Filesystem MCP

Servidor MCP para modificar arquivos com segurança em um diretório raiz do qual o usuário não deve conseguir escapar.

Playwright MCP

A server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without requiring screenshots or vision models.

The Web MCP

Enables AI assistants to access real-time web data through search, markdown scraping, and browser automation while bypassing anti-bot protections. It provides tools for web research, e-commerce monitoring, and data extraction from across the globe.

Vendor Risk Assessment MCP Server

Enables AI-powered vendor risk assessment using AWS Titan, allowing users to evaluate individual vendors, compare multiple vendors, and get industry risk benchmarks through natural language queries.

FastMail MCP Server

An MCP server that integrates with FastMail's JMAP API to manage mailboxes, search for emails, and send messages. It enables users to interact with their FastMail account for tasks like reading email content and managing folders through natural language.

Bilibili MCP

Enables searching for Bilibili videos through a standardized MCP interface, returning video information including title, author, view count, and duration with pagination support.

GitHub MCP Server

Exposes GitHub repository actions (listing PRs/issues, creating issues, merging PRs) as OpenAPI endpoints using FastAPI, designed for LLM agent orchestration frameworks.

Amazon MCP Server

Enables scraping Amazon product details and searching for products on Amazon through natural language queries. No API keys required as it scrapes publicly available Amazon pages.

MCP Servers

Uma coleção de servidores MCP (Model Context Protocol) como ferramentas dotnet.

HashiCorp Vault MCP Server

Enables interaction with HashiCorp Vault for secret management operations including reading, writing, listing, and deleting secrets through the Model Context Protocol.

Google Search MCP Server

Uma implementação de servidor MCP que se integra com a API JSON de Pesquisa Personalizada do Google, fornecendo capacidades de pesquisa na web.

Pytest MCP Server

Enables AI assistants to run and analyze pytest tests for desktop applications through interactive commands. Supports test execution, filtering, result analysis, and debugging for comprehensive test automation workflows.

flutterclimcp

Okay, here's a fun sample Flutter project idea using the Flutter CLI and a hypothetical "MCP (Model Context Protocol) Server" to illustrate how you might integrate data from an external source into your app: **Project Title:** "Recipe Roulette: What's for Dinner?" **Concept:** The app will randomly suggest recipes fetched from an MCP server. The MCP server, in this example, is a stand-in for any external API or data source that provides recipe information. **Why it's fun:** * **Practical:** Solves a common problem ("What should I cook?"). * **Randomness:** Adds an element of surprise. * **Extensible:** Easily expanded with features like filtering by cuisine, dietary restrictions, or ingredients. * **Illustrates Data Integration:** Demonstrates how to fetch and display data from an external source. **Steps (Assuming you have Flutter installed and configured):** **1. Project Setup (using Flutter CLI):** ```bash flutter create recipe_roulette cd recipe_roulette ``` **2. Hypothetical MCP Server (Conceptual - you'd need to implement this):** * **Imagine:** You have a server (written in Python, Node.js, Go, etc.) that exposes an endpoint like `/recipes/random`. * **Response:** This endpoint returns a JSON object representing a recipe: ```json { "id": 123, "name": "Spaghetti Carbonara", "ingredients": [ "Spaghetti", "Eggs", "Pancetta", "Pecorino Romano cheese", "Black pepper" ], "instructions": [ "Cook spaghetti according to package directions.", "Whisk eggs, cheese, and pepper.", "Fry pancetta until crispy.", "Combine everything and serve!" ], "imageUrl": "https://example.com/carbonara.jpg" } ``` **3. Flutter Code (Illustrative):** * **`lib/main.dart`:** ```dart import 'package:flutter/material.dart'; import 'dart:convert'; import 'package:http/http.dart' as http; void main() { runApp(const MyApp()); } class MyApp extends StatelessWidget { const MyApp({Key? key}) : super(key: key); @override Widget build(BuildContext context) { return MaterialApp( title: 'Recipe Roulette', theme: ThemeData( primarySwatch: Colors.blue, ), home: const RecipeRoulette(), ); } } class RecipeRoulette extends StatefulWidget { const RecipeRoulette({Key? key}) : super(key: key); @override _RecipeRouletteState createState() => _RecipeRouletteState(); } class _RecipeRouletteState extends State<RecipeRoulette> { Recipe? _recipe; bool _isLoading = false; Future<void> _fetchRecipe() async { setState(() { _isLoading = true; }); // Replace with your actual MCP server URL final url = Uri.parse('http://localhost:3000/recipes/random'); // Example URL try { final response = await http.get(url); if (response.statusCode == 200) { final jsonData = jsonDecode(response.body); setState(() { _recipe = Recipe.fromJson(jsonData); _isLoading = false; }); } else { // Handle error (e.g., show an error message) print('Error fetching recipe: ${response.statusCode}'); setState(() { _isLoading = false; }); ScaffoldMessenger.of(context).showSnackBar( const SnackBar(content: Text('Failed to load recipe.')), ); } } catch (e) { // Handle network errors print('Network error: $e'); setState(() { _isLoading = false; }); ScaffoldMessenger.of(context).showSnackBar( const SnackBar(content: Text('Network error. Please check your connection.')), ); } } @override Widget build(BuildContext context) { return Scaffold( appBar: AppBar( title: const Text('Recipe Roulette'), ), body: Center( child: _isLoading ? const CircularProgressIndicator() : _recipe == null ? const Text('Tap the button to get a recipe!') : RecipeCard(recipe: _recipe!), ), floatingActionButton: FloatingActionButton( onPressed: _fetchRecipe, tooltip: 'Get Recipe', child: const Icon(Icons.refresh), ), ); } } class Recipe { final int id; final String name; final List<String> ingredients; final List<String> instructions; final String? imageUrl; Recipe({ required this.id, required this.name, required this.ingredients, required this.instructions, this.imageUrl, }); factory Recipe.fromJson(Map<String, dynamic> json) { return Recipe( id: json['id'], name: json['name'], ingredients: List<String>.from(json['ingredients']), instructions: List<String>.from(json['instructions']), imageUrl: json['imageUrl'], ); } } class RecipeCard extends StatelessWidget { final Recipe recipe; const RecipeCard({Key? key, required this.recipe}) : super(key: key); @override Widget build(BuildContext context) { return Card( margin: const EdgeInsets.all(16.0), child: Padding( padding: const EdgeInsets.all(16.0), child: Column( crossAxisAlignment: CrossAxisAlignment.start, children: [ if (recipe.imageUrl != null) Image.network( recipe.imageUrl!, width: double.infinity, height: 200, fit: BoxFit.cover, errorBuilder: (context, error, stackTrace) { return const Text('Image not available'); }, ), Text( recipe.name, style: const TextStyle(fontSize: 24, fontWeight: FontWeight.bold), ), const SizedBox(height: 8), const Text( 'Ingredients:', style: TextStyle(fontSize: 18, fontWeight: FontWeight.bold), ), for (var ingredient in recipe.ingredients) Text('- $ingredient'), const SizedBox(height: 8), const Text( 'Instructions:', style: TextStyle(fontSize: 18, fontWeight: FontWeight.bold), ), for (var instruction in recipe.instructions) Text('- $instruction'), ], ), ), ); } } ``` **Explanation:** * **`Recipe` Class:** Represents the structure of a recipe. Includes `id`, `name`, `ingredients`, `instructions`, and an optional `imageUrl`. * **`RecipeRoulette` Widget:** * `_fetchRecipe()`: This is the core function. It makes an HTTP GET request to your hypothetical MCP server endpoint (`http://localhost:3000/recipes/random`). It uses the `http` package (you'll need to add it to your `pubspec.yaml` file). * Handles loading state (`_isLoading`) to show a `CircularProgressIndicator` while fetching data. * Parses the JSON response from the server using `jsonDecode`. * Creates a `Recipe` object from the parsed JSON. * Handles potential errors (e.g., server not found, invalid JSON). * **`RecipeCard` Widget:** Displays the recipe information in a nicely formatted card. * **`pubspec.yaml`:** Add the `http` package: ```yaml dependencies: flutter: sdk: flutter http: ^0.13.5 # Get the latest version from pub.dev ``` **4. Running the App:** 1. **Get Dependencies:** Run `flutter pub get` in your project directory. 2. **Run the App:** `flutter run` **Important Considerations:** * **MCP Server Implementation:** You'll need to *actually* create the MCP server. The code above assumes it exists and returns JSON in the specified format. You can use any language/framework you're comfortable with (Node.js with Express, Python with Flask/FastAPI, Go, etc.). A simple in-memory data structure (e.g., a list of recipe objects) is fine for a basic example. * **Error Handling:** The error handling in the example is basic. You should add more robust error handling (e.g., logging, more informative error messages to the user). * **Asynchronous Operations:** Fetching data from a server is an asynchronous operation. The `async` and `await` keywords are used to handle this. * **State Management:** For a more complex app, you might want to use a more sophisticated state management solution (Provider, Riverpod, BLoC, etc.). For this simple example, `setState` is sufficient. * **UI/UX:** This is a very basic UI. You can improve it with better styling, animations, and more user-friendly interactions. * **CORS:** If your Flutter app and MCP server are running on different domains (e.g., `localhost:5000` for the Flutter app and `localhost:3000` for the server), you'll need to configure CORS (Cross-Origin Resource Sharing) on your server to allow requests from your Flutter app's origin. **How to make it more fun:** * **Recipe Images:** Find a free API that provides recipe images (or use placeholder images). * **Animations:** Add animations when the recipe changes. * **User Preferences:** Allow users to filter recipes based on their preferences (e.g., cuisine, dietary restrictions). * **"Save" Recipes:** Let users save their favorite recipes to a list. * **Share Recipes:** Enable users to share recipes with friends. * **Voice Control:** Integrate voice control to fetch recipes using voice commands. This example provides a starting point. Adapt it to your specific needs and have fun building! Remember to replace the placeholder MCP server URL with the actual URL of your server. **Tradução para Português:** Aqui está uma ideia de projeto Flutter divertida usando o Flutter CLI e um hipotético "Servidor MCP (Model Context Protocol)" para ilustrar como você pode integrar dados de uma fonte externa em seu aplicativo: **Título do Projeto:** "Roleta de Receitas: O Que Tem Para Jantar?" **Conceito:** O aplicativo irá sugerir aleatoriamente receitas buscadas de um servidor MCP. O servidor MCP, neste exemplo, é um substituto para qualquer API ou fonte de dados externa que forneça informações sobre receitas. **Por que é divertido:** * **Prático:** Resolve um problema comum ("O que devo cozinhar?"). * **Aleatoriedade:** Adiciona um elemento de surpresa. * **Extensível:** Facilmente expandido com recursos como filtragem por culinária, restrições alimentares ou ingredientes. * **Ilustra a Integração de Dados:** Demonstra como buscar e exibir dados de uma fonte externa. **Passos (Assumindo que você tenha o Flutter instalado e configurado):** **1. Configuração do Projeto (usando o Flutter CLI):** ```bash flutter create recipe_roulette cd recipe_roulette ``` **2. Servidor MCP Hipotético (Conceitual - você precisaria implementar isso):** * **Imagine:** Você tem um servidor (escrito em Python, Node.js, Go, etc.) que expõe um endpoint como `/recipes/random`. * **Resposta:** Este endpoint retorna um objeto JSON representando uma receita: ```json { "id": 123, "name": "Spaghetti Carbonara", "ingredients": [ "Spaghetti", "Eggs", "Pancetta", "Pecorino Romano cheese", "Black pepper" ], "instructions": [ "Cook spaghetti according to package directions.", "Whisk eggs, cheese, and pepper.", "Fry pancetta until crispy.", "Combine everything and serve!" ], "imageUrl": "https://example.com/carbonara.jpg" } ``` **3. Código Flutter (Ilustrativo):** * **`lib/main.dart`:** (O código em Dart fornecido na resposta anterior) **Explicação:** * **Classe `Recipe`:** Representa a estrutura de uma receita. Inclui `id`, `name`, `ingredients`, `instructions` e um `imageUrl` opcional. * **Widget `RecipeRoulette`:** * `_fetchRecipe()`: Esta é a função principal. Ela faz uma requisição HTTP GET para o endpoint do seu servidor MCP hipotético (`http://localhost:3000/recipes/random`). Ela usa o pacote `http` (você precisará adicioná-lo ao seu arquivo `pubspec.yaml`). * Gerencia o estado de carregamento (`_isLoading`) para mostrar um `CircularProgressIndicator` enquanto busca os dados. * Analisa a resposta JSON do servidor usando `jsonDecode`. * Cria um objeto `Recipe` a partir do JSON analisado. * Lida com possíveis erros (por exemplo, servidor não encontrado, JSON inválido). * **Widget `RecipeCard`:** Exibe as informações da receita em um card formatado. * **`pubspec.yaml`:** Adicione o pacote `http`: ```yaml dependencies: flutter: sdk: flutter http: ^0.13.5 # Obtenha a versão mais recente de pub.dev ``` **4. Executando o Aplicativo:** 1. **Obtenha as Dependências:** Execute `flutter pub get` no diretório do seu projeto. 2. **Execute o Aplicativo:** `flutter run` **Considerações Importantes:** * **Implementação do Servidor MCP:** Você precisará *realmente* criar o servidor MCP. O código acima assume que ele existe e retorna JSON no formato especificado. Você pode usar qualquer linguagem/framework com a qual se sinta confortável (Node.js com Express, Python com Flask/FastAPI, Go, etc.). Uma estrutura de dados simples na memória (por exemplo, uma lista de objetos de receita) é suficiente para um exemplo básico. * **Tratamento de Erros:** O tratamento de erros no exemplo é básico. Você deve adicionar um tratamento de erros mais robusto (por exemplo, registro em log, mensagens de erro mais informativas para o usuário). * **Operações Assíncronas:** Buscar dados de um servidor é uma operação assíncrona. As palavras-chave `async` e `await` são usadas para lidar com isso. * **Gerenciamento de Estado:** Para um aplicativo mais complexo, você pode querer usar uma solução de gerenciamento de estado mais sofisticada (Provider, Riverpod, BLoC, etc.). Para este exemplo simples, `setState` é suficiente. * **UI/UX:** Esta é uma UI muito básica. Você pode melhorá-la com um estilo melhor, animações e interações mais amigáveis. * **CORS:** Se seu aplicativo Flutter e o servidor MCP estiverem sendo executados em domínios diferentes (por exemplo, `localhost:5000` para o aplicativo Flutter e `localhost:3000` para o servidor), você precisará configurar o CORS (Cross-Origin Resource Sharing) em seu servidor para permitir solicitações da origem do seu aplicativo Flutter. **Como tornar mais divertido:** * **Imagens de Receitas:** Encontre uma API gratuita que forneça imagens de receitas (ou use imagens de espaço reservado). * **Animações:** Adicione animações quando a receita mudar. * **Preferências do Usuário:** Permita que os usuários filtrem as receitas com base em suas preferências (por exemplo, culinária, restrições alimentares). * **"Salvar" Receitas:** Deixe os usuários salvarem suas receitas favoritas em uma lista. * **Compartilhar Receitas:** Permita que os usuários compartilhem receitas com amigos. * **Controle de Voz:** Integre o controle de voz para buscar receitas usando comandos de voz. Este exemplo fornece um ponto de partida. Adapte-o às suas necessidades específicas e divirta-se construindo! Lembre-se de substituir o URL do servidor MCP de espaço reservado pelo URL real do seu servidor.

mcp-lucene-server

mcp-lucene-server

DeFi Trading Agent MCP Server

Transforms AI assistants into autonomous crypto trading agents with real-time market analysis, portfolio management, and trade execution across 17+ blockchains.

Python Code Runner

Enables execution of Python code in a safe environment, including running scripts, installing packages, and retrieving variable values. Supports file operations and package management through pip.

MCP Servers

Servidores MCP de Código Aberto para Pesquisa Científica

LiblibAI Picture Generator

Enables AI image generation through LiblibAI API with natural language prompts. Supports various art styles, real-time progress tracking, and account credit management.

Integrator MCP Server

A Model Context Protocol server that allows AI assistants to invoke and interact with Integrator automation workflows through an API connection.

sliverc2-mcp

sliverc2-mcp

Trello MCP Server

Enables AI assistants to retrieve Trello card information by ID or link, providing access to card details including labels, members, due dates, and attachments through a standardized interface.

Pollinations Multimodal MCP Server

A Model Context Protocol server that enables AI assistants like Claude to generate images, text, and audio directly through Pollinations APIs using a lightweight stdio transport design.

icalPal MCP Server

Enables AI assistants to interact with macOS Calendar and Reminders applications. Allows querying events, tasks, calendars, and accounts through natural language using the icalPal Ruby gem.

Spotify MCP Server

Enables interaction with Spotify through natural language for music discovery, playback control, library management, and playlist creation. Supports searching for music, controlling playback, managing saved tracks, and getting personalized recommendations based on mood and preferences.

PitchLink MCP

An MCP server that reads startup pitch drafts from Notion to provide comprehensive investor-style analysis and scoring. It evaluates key areas like market opportunity and team strength, delivering feedback through a visual dashboard.

面试鸭 MCP Server

Serviço MCP Server para perguntas de busca do Interview Duck baseado em Spring AI, permitindo rapidamente que a IA busque perguntas e respostas reais de entrevistas corporativas.

Zen MCP Server

Orchestrates multiple AI models (Gemini, OpenAI, Claude, local models) within a single conversation context, enabling collaborative workflows like multi-model code reviews, consensus building, and CLI-to-CLI bridging for specialized tasks.