Discover Awesome MCP Servers

FakeStore MCP

A Model Context Protocol server that enables AI assistants to interact with a complete e-commerce application, providing authentication, product browsing, and shopping cart management through standardized MCP tools.

File Convert MCP Server

File Convert MCP Server

MCP Protocol Validator

Conjunto de pruebas para validar implementaciones de servidores MCP con respecto a la especificación del protocolo MCP abierto. Ayuda a los desarrolladores a garantizar el cumplimiento del protocolo y la interoperabilidad.

Moralis MCP Server

A TypeScript wrapper for the Moralis REST API that enables interaction with blockchain data through the Model Context Protocol (MCP).

Kollektiv

Kollektiv

ClickFunnels MCP Framework

Un servidor de Protocolo de Contexto de Modelo que integra ClickFunnels con Claude Desktop, permitiendo a los usuarios listar y recuperar embudos y contactos de su cuenta de ClickFunnels a través del lenguaje natural.

TheHive MCP Server

TheHive MCP Server

MCP2Brave

Un servidor basado en el protocolo MCP que utiliza la API de Brave para la funcionalidad de búsqueda web.

Laravel Forge MCP Server

A minimalist MCP server that integrates with Laravel Forge, allowing users to manage their Laravel Forge servers, sites, and deployments through AI assistants like Claude Desktop, Windsurf, or Cursor.

facebook-mcp-server

facebook-mcp-server

WhatsApp MCP Server

Implementación de un servidor MCP (Protocolo de Control de Mensajes) de WhatsApp.

Google Calendar MCP Server

Servidor de Protocolo de Contexto del Modelo (MCP) que se integra con la API de Google Calendar.

JMeter MCP Server

Un servidor de Protocolo de Contexto de Modelo que permite a los asistentes de IA ejecutar y gestionar pruebas de rendimiento de JMeter a través de comandos en lenguaje natural.

AI Agent with MCP

Okay, here's a basic outline and code snippets to help you create your first MCP (Model Context Protocol) server in a Playground environment. Keep in mind that MCP is a relatively new and evolving protocol, so the specific libraries and implementations might change. This example focuses on a simplified, conceptual approach. **Conceptual Overview** 1. **Choose a Language/Framework:** Python is a good choice for rapid prototyping and has libraries suitable for networking and data serialization. 2. **Define Your Model:** Decide what kind of model you want to serve. For a simple example, let's imagine a model that performs basic arithmetic (addition). 3. **Implement the MCP Server:** * Listen for incoming connections. * Receive MCP requests. * Parse the requests. * Execute the model (in our case, addition). * Format the response according to MCP. * Send the response. 4. **Implement a Simple MCP Client (for testing):** * Create a client to send requests to your server. * Receive and parse the responses. **Simplified Python Example (using `socket` and basic JSON)** ```python # server.py (This would run in your Playground) import socket import json HOST = '127.0.0.1' # Standard loopback interface address (localhost) PORT = 65432 # Port to listen on (non-privileged ports are > 1023) def handle_request(data): """ Simulates a simple model that performs addition. Assumes the data is a JSON string with 'a' and 'b' keys. """ try: request = json.loads(data.decode('utf-8')) a = request.get('a') b = request.get('b') if a is None or b is None: return json.dumps({"error": "Missing 'a' or 'b' parameter"}).encode('utf-8') try: result = a + b response = {"result": result} return json.dumps(response).encode('utf-8') except TypeError: return json.dumps({"error": "Invalid 'a' or 'b' value (must be numbers)"}).encode('utf-8') except json.JSONDecodeError: return json.dumps({"error": "Invalid JSON"}).encode('utf-8') with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() print(f"Server listening on {HOST}:{PORT}") conn, addr = s.accept() with conn: print(f"Connected by {addr}") while True: data = conn.recv(1024) # Receive up to 1024 bytes if not data: break # Client disconnected response = handle_request(data) conn.sendall(response) # Send the response back to the client ``` ```python # client.py (This would run in a separate Playground or terminal) import socket import json HOST = '127.0.0.1' # The server's hostname or IP address PORT = 65432 # The port used by the server with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) # Example request (MCP-like, but simplified) request_data = {"a": 5, "b": 3} request_json = json.dumps(request_data).encode('utf-8') s.sendall(request_json) data = s.recv(1024) print('Received:', repr(data.decode('utf-8'))) ``` **Explanation and Key Points:** * **`server.py`:** * Sets up a basic TCP socket server. * `handle_request()`: This is where your "model" logic goes. In this example, it's a simple addition function. It receives JSON data, parses it, performs the addition, and returns a JSON response. Error handling is included. * The server listens for connections, accepts a connection, and then enters a loop to receive data, process it, and send a response. * **`client.py`:** * Creates a TCP socket client. * Connects to the server. * Constructs a JSON request (representing an MCP-like request). * Sends the request to the server. * Receives the response and prints it. * **JSON for Serialization:** JSON is used for encoding and decoding the requests and responses. This is a common and relatively simple way to handle data serialization. * **Error Handling:** Basic error handling is included in the `handle_request` function to catch invalid JSON, missing parameters, and type errors. * **Simplified MCP:** This is *not* a full MCP implementation. It's a simplified example to illustrate the basic concepts. A real MCP implementation would involve more complex message structures, metadata, and potentially other protocols for data transfer. * **Playground Considerations:** Make sure your Playground environment allows network connections. Some online Playgrounds might have restrictions. If you have issues, try running the server and client on your local machine. * **Running the Code:** 1. Run `server.py` in one Playground or terminal window. 2. Run `client.py` in another Playground or terminal window. 3. The client should connect to the server, send the request, and print the response. **To make this more like a real MCP server, you would need to:** * **Define a formal MCP message structure:** MCP has specific requirements for the format of requests and responses, including metadata and data encoding. You'd need to adhere to those specifications. * **Implement a more sophisticated model:** Replace the simple addition with a more complex machine learning model. You might use libraries like TensorFlow, PyTorch, or scikit-learn. * **Handle different data types:** MCP needs to support various data types (images, text, etc.). You'd need to implement appropriate serialization and deserialization methods. * **Add authentication and authorization:** Secure your server to prevent unauthorized access. * **Consider performance:** Optimize your code for speed and efficiency, especially if you're serving a high volume of requests. **Important Considerations for Playgrounds:** * **Network Access:** Many online Playgrounds have limited or no network access. If you can't get the server and client to connect, it's likely a network restriction. Try running the code locally on your machine. * **Dependencies:** Make sure your Playground environment has the necessary libraries installed (e.g., `json`). If not, you might need to install them using `pip` or a similar package manager. * **File System Access:** Some Playgrounds might restrict file system access. If you need to load model files, you might need to find alternative ways to store and access them (e.g., using cloud storage). This example provides a starting point. You'll need to research the specific MCP specifications and adapt the code to your particular model and requirements. Remember to consult the official MCP documentation and any relevant libraries for more detailed information.

PDF Reader MCP Server (@shtse8/pdf-reader-mcp)

Un servidor MCP construido con Node.js/TypeScript que permite a agentes de IA leer de forma segura archivos PDF (locales o URL) y extraer texto, metadatos o el número de páginas. Utiliza pdf-parse.

Paradex Server

A Model Context Protocol server implementation that enables AI assistants to interact with the Paradex perpetual futures trading platform, allowing for retrieving market data, managing trading accounts, placing orders, and monitoring positions.

Fetch MCP Server

Proporciona funcionalidad para obtener y transformar contenido web en varios formatos (HTML, JSON, texto plano y Markdown) a través de simples llamadas a la API.

inked

inked

arXiv Search MCP Server

Un servidor MCP que proporciona herramientas para buscar y obtener artículos de arXiv.org.

Google Search Console MCP Server

Se conecta directamente a tu cuenta de Google Search Console a través de la API oficial, permitiéndote acceder a datos clave directamente desde herramientas de IA como Claude Desktop o OpenAI Agents SDK y otras.

Tinderbox MCP Server

Un servidor MCP para interactuar con la herramienta de gestión del conocimiento Tinderbox.

MCP Server for n8n Integration

A Model Context Protocol server that enables AI agents to interact with n8n workflows and automation tools through a standardized interface, allowing execution of workflows and access to n8n functions.

Pega DX MCP Server

Transforms complex Pega Platform interactions into intuitive, conversational experiences by exposing Pega DX APIs through the standardized Model Context Protocol, enabling AI applications to interact with Pega through natural language.

JinaAI Search

Permite una integración eficiente de búsqueda web con la API de búsqueda de Jina.ai, ofreciendo una recuperación de contenido limpia y optimizada para LLM, con soporte para varios tipos de contenido y almacenamiento en caché configurable.

MCP Client for Testing

Un cliente MCP minimalista para probar el servidor MCP.

DeepSeek Thinking with Claude 3.5 Sonnet

Facilita procesos de razonamiento en dos etapas utilizando DeepSeek para un análisis detallado y admite múltiples modelos de respuesta como Claude 3.5 Sonnet y OpenRouter, manteniendo el contexto de la conversación y mejorando las interacciones impulsadas por la IA.

Kakao Mobility & Kakao Map MCP Server

Mirror of

MCP Agent Platform

Un sistema de interacción persona-ordenador multiagente que permite la interacción natural a través de capacidades integradas de reconocimiento visual, reconocimiento de voz y síntesis de voz.