Discover Awesome MCP Servers

Whoop MCP Server

Exposes Whoop fitness data (recovery, sleep, strain, workouts) to Claude for use as a daily training coach, enabling natural language queries about your health metrics and training readiness.

Copper CRM MCP Server

Enables AI agents to read and manage Copper CRM data, including searching people, companies, and opportunities, listing pipelines, and logging activities or creating tasks.

Continuo Memory System

Enables persistent memory and semantic search for development workflows with hierarchical compression. Store and retrieve development knowledge across IDE sessions using natural language queries, circumventing context window limitations.

flashcard-mcp

A lightweight MCP server that adds spaced-repetition flashcards (SM-2) to AI assistants, storing data locally in SQLite and enabling card creation, review, and scheduling.

kef-mcp

MCP server for controlling KEF wireless speakers (LSX II, LS50 Wireless II, LS60) and playing Spotify on them via local network and Spotify Web API.

Spotinst MCP Server

An MCP server for the Spot.io API that enables management of AWS and Azure Ocean clusters across multiple accounts. It provides tools for cluster inventory, node management, cost analysis, and scaling operations through natural language.

CDRP-for-Claude

Shows your current Claude Desktop activity as Discord Rich Presence, including model, status, usage, and subscription info.

safe-omada-mcp

Security-focused MCP server for TP-Link Omada Open API workflows, enabling network management via natural language.

findata-mcp

A Financial Data Quality and AI Inference Evaluation MCP server that provides tools for auditing, bias detection, model evaluation, outlier scoring, A/B testing, and KPI reporting.

Internship Scout & Quality of Life MCP Server

Integrates Eurostat quality-of-life metrics and real-time job searching to help users find international internships in high-ranking European cities. It enables ranking cities based on personalized criteria like safety or transport and retrieves structured internship listings via the Tavily API.

mcp-mysql-apifox

MCP server for executing MySQL SQL, managing Apifox API documentation, and parsing/executing curl commands.

AskHumanToWork MCP Server

Enables AI agents to capture, manage, and retrieve todos with due dates and provenance, while automatically escalating reminders until tasks are completed.

ellmos-homebase-mcp

Enables local-first LLM orchestration with persistent memory, knowledge management, routing, swarm patterns, API probing, tests, automation planning, and plugin discovery via a stdio MCP server, using SQLite for offline storage.

CSMAR Web-API MCP

Enables MCP clients to search, browse, preview, and download CSMAR financial data using institutional IP authentication, no account or password required.

terminal-toolkit-mcp

Enables LLM clients to execute shell commands safely through the MCP protocol, with features like session management, safe mode, and process control.

icloud-mcp

MCP server for iCloud integration, providing tools for managing calendars, contacts, and email.

WhatsApp MCP

Send WhatsApp messages from your own personal number via AI assistant, with confirm-before-send and ability to read and summarize recent chats.

NannyKeeper MCP Server

Enables AI agents to calculate US household employer (nanny) taxes for all 50 states plus DC, including Social Security, Medicare, FUTA, and state unemployment, through natural language.

MCP with Langchain Sample Setup

Okay, here's a sample setup for a minimal MCP (Message Passing Communication) server and client in Python, designed to be compatible with LangChain. This example focuses on the core communication and doesn't include LangChain-specific logic within the server/client themselves. The idea is that you'd use this communication channel to send data to and from a LangChain agent or chain running on a separate server. **Important Considerations:** * **Simplicity:** This is a basic example. For production, you'd need to add error handling, security (authentication, encryption), more robust message formatting, and potentially asynchronous communication. * **LangChain Integration:** The LangChain part happens *outside* of this code. You'd use the client to send prompts to a LangChain agent running on the server and receive the agent's responses. * **Message Format:** I'm using JSON for simplicity. You could use other formats like Protocol Buffers for better performance and schema validation. * **Threading/Asyncio:** This example uses basic threading. For higher concurrency, consider using `asyncio`. **Code:** ```python import socket import threading import json # Server class MCPServer: def __init__(self, host='localhost', port=12345): self.host = host self.port = port self.server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM) self.server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1) # Allow reuse of address self.clients = [] # Keep track of connected clients def start(self): self.server_socket.bind((self.host, self.port)) self.server_socket.listen(5) # Listen for up to 5 incoming connections print(f"Server listening on {self.host}:{self.port}") while True: client_socket, addr = self.server_socket.accept() print(f"Accepted connection from {addr}") self.clients.append(client_socket) client_thread = threading.Thread(target=self.handle_client, args=(client_socket,)) client_thread.start() def handle_client(self, client_socket): try: while True: data = client_socket.recv(4096) # Receive up to 4096 bytes if not data: break # Client disconnected try: message = json.loads(data.decode('utf-8')) print(f"Received message: {message}") # **LangChain Integration Point:** # Here, you would pass the 'message' to your LangChain agent/chain # and get a response. For example: # response = my_langchain_agent.run(message['prompt']) # response_message = {'response': response} # self.send_message(client_socket, response_message) # For this example, just echo the message back: self.send_message(client_socket, {"response": f"Server received: {message}"}) except json.JSONDecodeError: print("Received invalid JSON data.") self.send_message(client_socket, {"error": "Invalid JSON"}) except Exception as e: print(f"Error handling client: {e}") finally: print(f"Closing connection with {client_socket.getpeername()}") self.clients.remove(client_socket) client_socket.close() def send_message(self, client_socket, message): try: message_json = json.dumps(message) client_socket.sendall(message_json.encode('utf-8')) except Exception as e: print(f"Error sending message: {e}") def stop(self): for client in self.clients: client.close() self.server_socket.close() print("Server stopped.") # Client class MCPClient: def __init__(self, host='localhost', port=12345): self.host = host self.port = port self.client_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM) def connect(self): try: self.client_socket.connect((self.host, self.port)) print(f"Connected to server at {self.host}:{self.port}") return True except socket.error as e: print(f"Connection error: {e}") return False def send_message(self, message): try: message_json = json.dumps(message) self.client_socket.sendall(message_json.encode('utf-8')) data = self.client_socket.recv(4096) if data: response = json.loads(data.decode('utf-8')) return response else: return None except Exception as e: print(f"Error sending/receiving message: {e}") return None def close(self): self.client_socket.close() print("Connection closed.") # Example Usage (in separate files or at the end of the same file) if __name__ == "__main__": # Server Example server = MCPServer() server_thread = threading.Thread(target=server.start) server_thread.daemon = True # Allow the main thread to exit even if the server thread is running server_thread.start() # Client Example import time time.sleep(1) # Give the server a moment to start client = MCPClient() if client.connect(): message = {"prompt": "What is the capital of France?"} response = client.send_message(message) if response: print(f"Received response: {response}") else: print("No response received.") client.close() server.stop() # Stop the server after the client is done. ``` **Explanation:** 1. **`MCPServer` Class:** * `__init__`: Initializes the server socket, host, and port. `setsockopt` allows reusing the address, which is helpful for quick restarts. * `start`: Binds the socket, listens for connections, and spawns a new thread for each client that connects. * `handle_client`: This is the core of the server. It receives data from the client, decodes it as JSON, and then (crucially) this is where you would integrate with your LangChain agent or chain. The example code just echoes the message back. It also handles JSON decoding errors. * `send_message`: Encodes a message as JSON and sends it to the client. * `stop`: Closes all client connections and the server socket. 2. **`MCPClient` Class:** * `__init__`: Initializes the client socket, host, and port. * `connect`: Connects to the server. * `send_message`: Encodes a message as JSON, sends it to the server, receives the response, decodes the response as JSON, and returns it. * `close`: Closes the client socket. 3. **Example Usage:** * Creates a server instance and starts it in a separate thread (using `threading.Thread`). The `daemon = True` makes the server thread exit when the main thread exits. * Creates a client instance, connects to the server, sends a message (a prompt), receives the response, and prints the response. * Closes the client connection. * Stops the server. **How to Run:** 1. Save the code as a Python file (e.g., `mcp_example.py`). 2. Run the file from your terminal: `python mcp_example.py` You should see output from both the server and the client. The client will send a message, and the server will echo it back. **LangChain Integration (Conceptual):** The key part is in the `handle_client` method of the `MCPServer` class. Instead of just echoing the message, you would do something like this: ```python # Inside the handle_client method: try: message = json.loads(data.decode('utf-8')) print(f"Received message: {message}") # **LangChain Integration:** from langchain.llms import OpenAI # Or your preferred LLM from langchain.chains import LLMChain from langchain.prompts import PromptTemplate # Example using OpenAI and a simple prompt llm = OpenAI(temperature=0.7, openai_api_key="YOUR_OPENAI_API_KEY") # Replace with your API key prompt_template = PromptTemplate.from_template("{prompt}") chain = LLMChain(llm=llm, prompt=prompt_template) response = chain.run(message['prompt']) # Run the LangChain chain response_message = {'response': response} self.send_message(client_socket, response_message) except json.JSONDecodeError: print("Received invalid JSON data.") self.send_message(client_socket, {"error": "Invalid JSON"}) ``` **Important Notes for LangChain:** * **Install LangChain:** `pip install langchain openai` (or other necessary packages). * **API Keys:** You'll need to set up your API keys for the LLMs you're using (e.g., OpenAI). Don't hardcode them directly in the code; use environment variables or a configuration file. * **Error Handling:** Add more robust error handling around the LangChain calls. * **Prompt Engineering:** The quality of your prompts will greatly affect the results. * **Asynchronous Communication (Advanced):** For high-volume scenarios, consider using `asyncio` for both the server and the client to handle multiple requests concurrently. This will significantly improve performance. **Spanish Translation of Key Concepts:** * **Server:** Servidor * **Client:** Cliente * **Message:** Mensaje * **Prompt:** Indicación, Instrucción * **Response:** Respuesta * **Socket:** Zócalo (although "socket" is often used directly in technical contexts) * **Connection:** Conexión * **Thread:** Hilo * **JSON:** JSON (pronounced the same) * **LangChain Agent:** Agente de LangChain * **LangChain Chain:** Cadena de LangChain * **API Key:** Clave API This comprehensive example should give you a solid foundation for building an MCP server and client that can communicate with a LangChain agent. Remember to adapt the code to your specific needs and add the necessary error handling and security measures.

steps-mcp

Task planning and execution MCP server with durable SQLite storage and a browser UI for reviewing plans and following progress.

Resend MCP Server

Enables sending emails via the Resend API from Claude, with tools for sending, checking delivery status, listing recent emails, and managing domains.

GraphMemory-IDE

An AI-assisted, long-term memory system for IDEs, powered by Kuzu graph database. GraphMemory-IDE is an MCP server that provides semantic vector search, graph-based knowledge storage, and real-time analytics.

Mirdan

Automatically enhances developer prompts with quality requirements, codebase context, and architectural patterns, then orchestrates other MCP servers to ensure AI coding assistants produce high-quality, structured code that follows best practices and security standards.

tokencast

Pre-execution cost estimation for LLM agent workflows, providing cost estimates before running tasks and improving accuracy over time through calibration.

gemini-image-mcp

Enables Claude Code to generate and edit images using Google's Gemini and Imagen models on Vertex AI, with support for multiple models, aspect ratios, and image fusion.

linux-computer-use

MCP server enabling AI agents to control a real Linux browser with live view, human takeover, and safety guardrails.

playwright-mcp-server

Deploys a stateless remote MCP server on Cloudflare Workers without authentication, enabling tools to be used with Cloudflare AI Playground or local clients like Claude Desktop.

oaid-mcp

Enables AI agents to securely use Open Agent ID credentials for signing requests, looking up agent data, and exchanging encrypted messages. It performs all cryptographic operations within the server process to ensure private keys are never exposed to the AI agent.

SEOforGPT MCP Server

Enables AI-driven brand visibility monitoring and SEO project management via the SEOforGPT API. Users can execute brand visibility checks, list projects, and retrieve detailed visibility reports through natural language interactions.

scopa-mcp-server

An MCP server for playing the Italian card game Scopa, supporting 2-4 players, Redis-backed event logging, real-time synchronization, and an optional LLM opponent.