Discover Awesome MCP Servers

FastMCP LaTeX Server (tex-mcp)

MCP server that renders LaTeX to PDF via pdflatex, supporting raw LaTeX and Jinja2 templates with artifact generation.

dns-whois-mcp

FastMCP server for DNS lookups and WHOIS domain research, enabling comprehensive domain investigation with parallel DNS records, WHOIS, and reverse lookups.

MCP File System Agent

An agentic file-system assistant that lets users read, write, list, and search local files through natural language, using a LangChain agent with an Ollama LLM backed by a FastMCP server.

typescript-mcp-server

A TypeScript boilerplate for building Model Context Protocol (MCP) servers with example tools (calculator, greet) and resources (system info).

velesdb-memory

Local-first agent-memory MCP server with a why() tool: recall a fact together with its connected subgraph (multi-hop), so linked memories surface even when they share no words with the query. remember/recall/relate/forget/why over one fused vector + graph + columnar engine a single offline Rust binary.

App Store Connect MCP Server

Enables interaction with Apple's App Store Connect API through natural language to manage apps, beta testing, localizations, analytics, sales reports, and CI/CD workflows for iOS and macOS development.

mcp-agent-toolkit

An MCP server exposing three tools — a read-only PostgreSQL commerce database, a live weather API, and a calculator — behind a real MCP protocol client/server boundary. It enables natural-language questions that combine database and weather data, with real-time streaming of tool calls and model error recovery.

datagovma-mcp

MCP server for the Moroccan Open Data portal (data.gov.ma) enabling search and retrieval of datasets, resources, organizations, and groups via CKAN API.

Baby-SkyNet

Provides Claude AI with persistent, searchable memory management across sessions using SQL database, semantic analysis with multi-provider LLM support (Anthropic/Ollama), vector search via ChromaDB, and graph-based knowledge relationships through Neo4j integration.

obsidian-vault-mcp

An MCP server for Obsidian vaults that handles iCloud eviction gracefully, allowing reading, searching, creating, and updating notes without hanging.

mcp_server

Okay, here's a basic outline and example code snippets to guide you in implementing a sample MCP (Media Control Protocol) server using a Dolphin MCP client. This will be a simplified example to illustrate the core concepts. **Understanding the Components** * **MCP (Media Control Protocol):** A protocol for controlling media playback devices. It defines commands like play, pause, stop, seek, and volume control. * **Dolphin MCP Client:** A library or tool (presumably you have access to this) that acts as the client in the MCP communication. It sends commands to the MCP server. * **MCP Server:** The application you'll build. It listens for MCP commands from the Dolphin MCP client, interprets them, and then performs the corresponding actions (e.g., controlling a media player). **High-Level Steps** 1. **Choose a Programming Language and Framework:** Python is a good choice for its simplicity and networking libraries. You could use the `socket` module directly or a framework like `asyncio` for asynchronous handling. 2. **Set up a Socket Server:** Create a socket server that listens on a specific port (e.g., 5000). This server will accept connections from the Dolphin MCP client. 3. **Receive and Parse MCP Commands:** When a client connects, receive data from the socket. This data will be the MCP command. You'll need to parse the command string to determine the action to perform. 4. **Implement Command Handlers:** Create functions or methods to handle each MCP command (e.g., `handle_play()`, `handle_pause()`, `handle_seek()`). These handlers will interact with your media player (or a simulated media player for testing). 5. **Send Responses (Optional):** The MCP protocol may define response messages. You can send acknowledgements or status updates back to the client. 6. **Error Handling:** Implement error handling to gracefully deal with invalid commands, network issues, and other potential problems. **Python Example (using `socket` module)** ```python import socket import threading HOST = '127.0.0.1' # Loopback address (localhost) PORT = 5000 # Port to listen on # Simulated Media Player (replace with actual media player control) class MediaPlayer: def __init__(self): self.playing = False self.position = 0 # in seconds self.volume = 100 def play(self): print("Playing...") self.playing = True def pause(self): print("Pausing...") self.playing = False def stop(self): print("Stopping...") self.playing = False self.position = 0 def seek(self, position): print(f"Seeking to {position} seconds...") self.position = position def set_volume(self, volume): print(f"Setting volume to {volume}%") self.volume = volume media_player = MediaPlayer() # Create an instance of the media player def handle_client(conn, addr): print(f"Connected by {addr}") try: while True: data = conn.recv(1024) # Receive up to 1024 bytes if not data: break command = data.decode('utf-8').strip() # Decode and remove whitespace print(f"Received command: {command}") # Parse the command (very basic example) parts = command.split() action = parts[0].lower() if action == "play": media_player.play() conn.sendall(b"OK\n") # Send a simple acknowledgement elif action == "pause": media_player.pause() conn.sendall(b"OK\n") elif action == "stop": media_player.stop() conn.sendall(b"OK\n") elif action == "seek": try: position = int(parts[1]) media_player.seek(position) conn.sendall(b"OK\n") except (IndexError, ValueError): conn.sendall(b"ERROR: Invalid seek command\n") elif action == "volume": try: volume = int(parts[1]) media_player.set_volume(volume) conn.sendall(b"OK\n") except (IndexError, ValueError): conn.sendall(b"ERROR: Invalid volume command\n") else: print(f"Unknown command: {command}") conn.sendall(b"ERROR: Unknown command\n") except Exception as e: print(f"Error handling client: {e}") finally: conn.close() print(f"Connection closed with {addr}") def main(): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() print(f"Listening on {HOST}:{PORT}") while True: conn, addr = s.accept() thread = threading.Thread(target=handle_client, args=(conn, addr)) thread.start() if __name__ == "__main__": main() ``` **Explanation:** 1. **Imports:** Imports the necessary modules (`socket` for networking, `threading` for handling multiple clients concurrently). 2. **Constants:** Defines the host and port for the server. 3. **`MediaPlayer` Class:** A simple class to simulate a media player. Replace the placeholder methods with actual media player control code (e.g., using a library like `vlc` or `pygame`). 4. **`handle_client(conn, addr)` Function:** * This function is executed in a separate thread for each client connection. * It receives data from the client using `conn.recv(1024)`. * It decodes the data (assuming UTF-8 encoding) and removes leading/trailing whitespace. * It parses the command string (very basic splitting on spaces). **Important:** A real MCP implementation would likely have a more robust parsing mechanism. * It calls the appropriate `media_player` methods based on the command. * It sends a simple "OK" or "ERROR" response back to the client. * It includes error handling to catch exceptions. * It closes the connection when the client disconnects or an error occurs. 5. **`main()` Function:** * Creates a socket object using `socket.socket(socket.AF_INET, socket.SOCK_STREAM)`. * Binds the socket to the specified host and port using `s.bind((HOST, PORT))`. * Starts listening for incoming connections using `s.listen()`. * Enters a loop that accepts incoming connections using `s.accept()`. * For each connection, it creates a new thread to handle the client using `threading.Thread(target=handle_client, args=(conn, addr))`. * Starts the thread using `thread.start()`. 6. **`if __name__ == "__main__":`:** Ensures that the `main()` function is only executed when the script is run directly (not when it's imported as a module). **How to Run:** 1. Save the code as a Python file (e.g., `mcp_server.py`). 2. Run the script from your terminal: `python mcp_server.py` 3. Use the Dolphin MCP client to connect to `127.0.0.1` on port `5000`. 4. Send MCP commands like "play", "pause", "stop", "seek 10", "volume 50". Observe the output in the server's terminal. **Important Considerations and Improvements:** * **MCP Protocol Specification:** You *must* have the full specification for the MCP protocol you're using. This example is a very simplified approximation. The specification will define the exact command formats, data types, and response codes. * **Robust Command Parsing:** Use a more robust parsing method (e.g., regular expressions, a dedicated parsing library) to handle complex command formats and arguments. * **Error Handling:** Implement comprehensive error handling to catch invalid commands, network errors, and other potential issues. Provide informative error messages to the client. * **Asynchronous I/O:** For a more scalable server, consider using `asyncio` for asynchronous I/O. This allows the server to handle multiple clients concurrently without using threads. * **Media Player Integration:** Replace the `MediaPlayer` class with actual code to control your media player. You might need to use a library specific to your media player (e.g., `vlc`, `pygame`, or a media player's API). * **Security:** If the MCP server will be exposed to a network, consider security implications and implement appropriate security measures (e.g., authentication, authorization, encryption). * **Threading vs. Asynchronous:** For a small number of clients, threading might be sufficient. For a larger number of clients, asynchronous I/O is generally more efficient. * **Dolphin MCP Client Documentation:** Refer to the Dolphin MCP client's documentation for details on how to connect to the server and send commands. **Example Commands from Dolphin MCP Client:** Assuming the Dolphin MCP client sends commands as simple text strings: * `PLAY` * `PAUSE` * `STOP` * `SEEK 60` (Seek to 60 seconds) * `VOLUME 75` (Set volume to 75%) **Indonesian Translation of Key Concepts:** * **MCP (Media Control Protocol):** Protokol Kontrol Media * **Dolphin MCP Client:** Klien Dolphin MCP * **MCP Server:** Server MCP * **Socket:** Soket * **Command:** Perintah * **Parse:** Mengurai (or Memproses) * **Handler:** Penangan * **Response:** Respon * **Error Handling:** Penanganan Kesalahan * **Media Player:** Pemutar Media * **Thread:** Utas (or Alur) * **Asynchronous I/O:** I/O Asinkron This detailed explanation and code example should give you a solid starting point for implementing your MCP server. Remember to adapt the code to your specific needs and the requirements of the Dolphin MCP client and the MCP protocol you're using. Good luck!

Guardian News MCP Server

Enables users to search for the latest news articles from The Guardian using keywords and check service status. Provides access to Guardian's news content through their API with configurable result limits.

sc-mcp

Connects your Scalable Capital brokerage to any MCP-capable assistant, providing read-only access to portfolio, trades, analytics, quotes, charts, watchlist, and alerts via the official sc CLI.

datalastic-mcp

MCP server that enables AI assistants to access real-time vessel tracking, port information, and maritime data through the Datalastic Marine AIS Data API.

mcp-local-image-reader

A simple MCP server that reads local images and returns them as ImageContent for LLM vision analysis.

MCP SQLite Server

Query, explore, and manage SQLite databases through the Model Context Protocol. Connect any MCP-compatible AI client to your databases.

Slack MCP Server

A FastMCP-based server that provides complete Slack integration for Cursor IDE, allowing users to interact with Slack API features using natural language.

jioaicloud-mcp-server

Local MCP server for managing JioAICloud backups from Cursor, enabling browsing, duplicate detection, safe trashing, album management, and inventory exports using your own account.

godot-mcp-bridge

Let Claude, Cursor, or any MCP-compatible AI work inside your Godot project: read and edit scenes, write and validate scripts, run the game, drive it, and read the errors — without copy-pasting anything.

Banking MCP Server

A comprehensive banking system with MCP server capabilities and REST API, enabling account management, deposits, withdrawals, transfers, and transaction history through natural language or HTTP endpoints.

Whalesync MCP server

Enables AI agents to create, manage, and monitor two-way data syncs between platforms like Airtable, Webflow, HubSpot, Salesforce, Notion, and Postgres, including mapping fields, running syncs, and troubleshooting record-level issues.

Neuratel MCP Server

Control your voice AI platform through natural language from any MCP-compatible assistant.

Basic MCP Server

A minimal Model Context Protocol (MCP) server demonstrating the implementation of tools, resources, and prompts. It serves as a starter template built with the Smithery SDK for developing custom integrations.

UNHCR Open Data Gateway MCP

Provides a unified interface to access UNHCR's open data across statistics, RDF, and IATI MCP servers, enabling aggregated queries, cross-domain analytics, and dataset discovery.

CropProphEU

EU Crop Intelligence MCP Server — Yield forecasts, weather analysis, and phenology models for 15 countries. AI agent-native, multi-source intelligence (NASA POWER, Eurostat, Open-Meteo).

twitch-mcp

This project is a fork and expansion of TomCools' Twitch MCP Server, which implements a Model Context Protocol (MCP) server that integrates with Twitch chat, allowing AI assistants like Claude to interact with your Twitch channel.

nxopen-mcp

Provides AI coding agents with accurate knowledge of the Siemens NXOpen .NET API by performing hybrid retrieval over local documentation, eliminating hallucinated API calls.

Wise MCP Server

Enables access to Wise API functionality for managing recipients and sending money transfers. Supports listing recipients, creating new recipients, validating account details, and executing money transfers with authentication handling.

VibeGuard MCP Server

Enables AI coding tools to scan projects for security vulnerabilities, hardcoded secrets, injection flaws, and privacy violations with 699 rules and 76 MCP tools, all running locally with zero telemetry.