Discover Awesome MCP Servers

MCP iCal Server

Agent-powered calendar management for macOS that transforms natural language into calendar operations through a single MCP tool interface.

Rootly MCP Server for Cloudflare Workers

A remote MCP server that provides AI agents access to the Rootly API for incident management, allowing users to query and manage incidents, alerts, teams, services, and other incident management resources through natural language.

A2AMCP

A Redis-backed MCP server that enables multiple AI agents to communicate, coordinate, and collaborate while working on parallel development tasks, preventing conflicts in shared codebases.

Anki MCP Server

Enables interaction with the Anki desktop app for spaced repetition learning. Supports reviewing due cards, creating new flashcards, and managing study sessions through natural language commands.

grasp

Self-hosted Browser Using Agent with built-in MCP, A2A support.

Codebase MCP Server

Enables AI assistants to semantically search and understand code repositories using PostgreSQL with pgvector embeddings. Provides repository indexing, natural language code search, and development task management with git integration.

GitHub Configuration

Server Protokol Konteks Model (MCP) untuk aplikasi manajemen tugas TickTick.

Knowledge Tools Mcp

Sebuah server MCP untuk berinteraksi dengan berbagai aplikasi penelitian dan pencatatan.

Pilldoc User MCP

Provides access to pharmaceutical management system APIs including user authentication, pharmacy account management, and advertising campaign controls. Enables querying pharmacy information, updating account details, and managing ad blocking through natural language interactions.

HubAPI Auth MCP Server

An MCP server for interacting with HubSpot's authentication API, enabling secure authentication and authorization operations through natural language.

Financial Data MCP Server

A Model Context Protocol server that provides financial tools for retrieving real-time stock data, analyst recommendations, financial statements, and web search capabilities for a LangGraph-powered ReAct agent.

Naver Search MCP Server

Provides access to Naver Search APIs, allowing AI agents to search across multiple categories (blogs, news, books, images, shopping items, etc.) with structured responses optimized for LLM consumption.

OpenFeature MCP Server

Provides OpenFeature SDK installation guidance through MCP tool calls. Enables AI clients to fetch installation prompts and setup instructions for various OpenFeature SDKs across different programming languages and frameworks.

RobotFrameworkLibrary-to-MCP

Okay, here's a breakdown of how to turn a Robot Framework library into an MCP (Message Center Protocol) server, along with explanations and considerations: **Understanding the Goal** The core idea is to expose the functionality of your Robot Framework library as a service that can be accessed remotely via MCP. This allows other systems (clients) to call the keywords in your library without needing to run Robot Framework directly on the client machine. **Key Components and Concepts** 1. **Robot Framework Library:** This is your existing library containing the keywords you want to expose. 2. **MCP Server:** A server that listens for MCP requests, processes them, and sends back responses. You'll need to implement this server. 3. **MCP Client:** The system that sends requests to your MCP server to execute keywords. 4. **Serialization/Deserialization:** MCP involves sending data (keyword names, arguments, return values) over a network. You'll need to serialize data into a format suitable for transmission (e.g., JSON, XML, Protocol Buffers) and deserialize it on the other end. **General Steps** 1. **Choose an MCP Implementation (or Build Your Own):** * **Existing MCP Libraries (Python):** Check if there are existing Python libraries that provide MCP server/client functionality. Search for "Python MCP library" or "Message Center Protocol Python." If you find a suitable library, it will greatly simplify the process. I don't have specific recommendations without knowing your exact requirements, but this is the first place to look. * **Roll Your Own (using sockets):** If you can't find a suitable library, you'll need to implement the MCP protocol yourself using Python's socket library. This is more complex but gives you full control. You'll need to understand the MCP specification. 2. **Create the MCP Server (Python):** * **Import Your Robot Framework Library:** In your Python MCP server code, import the Robot Framework library you want to expose. * **Listen for Connections:** Use the chosen MCP library (or socket code) to listen for incoming connections on a specific port. * **Receive MCP Requests:** When a client connects, receive the MCP request. The request will typically contain: * The name of the Robot Framework keyword to execute. * The arguments to pass to the keyword. * **Deserialize the Request:** Convert the received data (e.g., JSON string) into Python data structures (e.g., a dictionary or list). * **Execute the Keyword:** ```python # Assuming you have your library imported as 'mylibrary' def handle_mcp_request(keyword_name, args): try: # Use getattr to dynamically call the keyword keyword_function = getattr(mylibrary, keyword_name) result = keyword_function(*args) # Execute the keyword return result, None # Return result and no error except Exception as e: return None, str(e) # Return None and the error message ``` * **Serialize the Response:** Convert the result (or any error message) into a format suitable for sending back to the client (e.g., JSON). * **Send the Response:** Send the serialized response back to the client. * **Close the Connection:** Close the connection with the client. 3. **Create the MCP Client (Python or other language):** * **Connect to the Server:** Use the chosen MCP library (or socket code) to connect to the MCP server's address and port. * **Create the MCP Request:** Construct the MCP request, including the keyword name and arguments. * **Serialize the Request:** Convert the request data into the chosen format (e.g., JSON). * **Send the Request:** Send the serialized request to the server. * **Receive the Response:** Receive the response from the server. * **Deserialize the Response:** Convert the received data back into Python data structures. * **Process the Result:** Handle the result (or any error message) returned by the server. * **Close the Connection:** Close the connection with the server. **Example (Illustrative - Using Sockets and JSON for Simplicity)** This is a simplified example to illustrate the concepts. It's not a complete, production-ready solution. *Server (server.py)* ```python import socket import json import mylibrary # Your Robot Framework library 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): try: request = json.loads(data.decode('utf-8')) keyword_name = request['keyword'] args = request['args'] keyword_function = getattr(mylibrary, keyword_name) result = keyword_function(*args) return json.dumps({'result': result, 'error': None}) except Exception as e: return json.dumps({'result': None, 'error': str(e)}) 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) if not data: break response = handle_request(data) conn.sendall(response.encode('utf-8')) ``` *Client (client.py)* ```python 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)) request = { 'keyword': 'my_keyword', # Replace with your keyword name 'args': ['arg1', 'arg2'] # Replace with your arguments } request_json = json.dumps(request) s.sendall(request_json.encode('utf-8')) data = s.recv(1024) print('Received:', repr(data)) ``` *Example Robot Framework Library (mylibrary.py)* ```python def my_keyword(arg1, arg2): """This is a sample keyword.""" return f"Keyword called with {arg1} and {arg2}" def another_keyword(number): return number * 2 ``` **Important Considerations** * **Error Handling:** Robust error handling is crucial. Catch exceptions in the server and send meaningful error messages back to the client. * **Security:** If you're exposing this service over a network, consider security implications. Use encryption (e.g., TLS/SSL) to protect the data in transit. Implement authentication and authorization to control who can access the service. * **Data Types:** Be mindful of data types when serializing and deserializing. Ensure that the client and server agree on how to represent data (e.g., dates, numbers). * **Concurrency:** If you expect multiple clients to connect simultaneously, you'll need to handle concurrency in your server (e.g., using threads or asynchronous programming). * **MCP Specification:** If you are implementing the MCP protocol yourself, carefully study the MCP specification to ensure compliance. * **Existing Libraries:** Before you start writing a lot of code, thoroughly research existing Python libraries that might provide MCP functionality. This can save you a significant amount of time and effort. **How to Run the Example** 1. **Save the files:** Save the code as `server.py`, `client.py`, and `mylibrary.py` in the same directory. 2. **Run the server:** Open a terminal and run `python server.py`. 3. **Run the client:** Open another terminal and run `python client.py`. The client will send a request to the server, the server will execute the `my_keyword` function from `mylibrary.py`, and the client will print the response. Remember to replace `"my_keyword"` and the arguments in `client.py` with the actual keyword and arguments from your Robot Framework library. Also, replace `mylibrary` in `server.py` with the actual name of your library. This detailed explanation and example should give you a solid foundation for turning your Robot Framework library into an MCP server. Good luck!

Zulip MCP Server

A Model Context Protocol server that enables AI assistants to interact with Zulip workspaces by exposing REST API capabilities as tools for message operations, channel management, and user interactions.

MCP Server TypeScript Starter

A Model Context Protocol (MCP) server that provides location services

Devpipe MCP Server

Enables AI assistants to interact with devpipe, a local pipeline runner, allowing them to list tasks, run pipelines, validate configurations, debug failures, analyze security findings, and generate CI/CD configs through natural language.

Roblox MCP Unified Server

Comprehensive Roblox development server with 8 tools for managing Lua/Luau scripts including creation, validation, backup/restore, and project management with SQLite storage and HMAC authentication.

MCP Agents Server

Facilitates interaction and context sharing between AI models using the standardized Model Context Protocol (MCP) with features like interoperability, scalability, security, and flexibility across diverse AI systems.

Time MCP Server

Provides current time information and timezone conversion capabilities using IANA timezone names. Enables LLMs to get current time in any timezone and convert times between different timezones with automatic system timezone detection.

FSS Pension MCP Server

Provides FSS (Korean Financial Supervisory Service) pension data to AI models like Claude through Model Context Protocol, enabling real-time pension product information retrieval and personalized AI-based pension consultation services.

Jinko

Jinko

Remote MCP Server

A Cloudflare Workers-based MCP server that allows users to deploy and customize tools without authentication requirements, compatible with Cloudflare AI Playground and Claude Desktop.

Hong Kong Transportation MCP Server

An MCP server providing access to Hong Kong transportation data, including passenger traffic statistics at control points and real-time bus arrival information for KMB and Long Win Bus services.

bigquery-mcp

Server MCP untuk membantu Agen AI memeriksa isi gudang BigQuery.

SAP Concur MCP Server by CData

This read-only MCP Server allows you to connect to SAP Concur data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp

mcp_repo_170d1d13

Ini adalah repositori pengujian yang dibuat oleh skrip pengujian MCP Server untuk GitHub.

MCP Troubleshooter

A specialized diagnostic framework that enables AI models to self-diagnose and fix MCP-related issues by analyzing logs, validating configurations, testing connections, and implementing solutions.