Discover Awesome MCP Servers

Pedalpalooza MCP Server

Fetches bike ride events from the Pedalpalooza calendar and allows LLMs to query rides by date, pace, difficulty, and family-friendliness.

legalize-mcp

A read-only MCP server providing access to national legislation from 37 jurisdictions via the legalize-dev corpus, with tools for searching, retrieving laws, and browsing reform history.

mcp-session-insight

Enables AI assistants to query and analyze past Claude Code sessions, providing structured insights like file changes, decisions, errors, and git history across projects.

MCP RSS News Agent

A FastMCP-based server that provides tools for discovering RSS feeds, fetching and processing news content, searching articles by keyword, and generating summaries across multiple news sources and categories.

CSMAR MCP Server

Enables direct access to CSMAR financial databases through Claude Code. Supports 240+ databases including financial statements, stock trading data, and company information with intelligent login management and 11 MCP tools.

MCP Hello World Server

A demonstration Model Context Protocol server that provides a configurable 'Hello World' tool with multi-language support and input validation. It supports both local stdio and remote HTTP deployment via Docker, facilitating testing and integration with platforms like Cursor and Manus.

vibeMK

Enables complete management of CheckMK monitoring environments through natural language, including live monitoring, downtime scheduling, problem management, and configuration.

PyNet Bridge

PyNet Bridge MCP implementation to connect IAs with PyNet Platform.

Landlaw AI MCP

Landlaw AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

mcp-eyes

A drop-in MCP server that pairs long-context reasoning LLMs with vision models in description-only mode, enabling any reasoning model to 'see' images without the vision model giving advice or solutions.

WeaveTab-MCP

The Zero-Setup Local Browser MCP. Enables AI agents to control web browsers via CDP with zero vision tokens and high-speed DOM mapping.

Keboola Explorer MCP Server

This server facilitates interaction with Keboola's Storage API, enabling users to browse and manage project buckets, tables, and components efficiently through Claude Desktop.

LINE Shopping API MCP

MCP Server for the LINE Shopping API, enabling AI agents and tools to interact with LINE Shopping data and operations via the Model Context Protocol.

zopaf-mcp

Negotiation math engine for AI agents. Computes Pareto frontiers, generates iso-utility counteroffers, and infers counterpart priorities. 9 tools for any multi-issue negotiation. Zero LLM tokens — pure MILP optimization.

MCP OpenDART

Enables AI assistants to access South Korea's financial disclosure system (OpenDART), allowing users to retrieve corporate financial reports, disclosure documents, shareholder information, and automatically extract and search financial statement notes through natural language queries.

Coconuts MCP Server

Enables management of Google Maps saved places through a SQLite database. Allows users to store, query, and organize their Google Maps places data locally.

fastmcp-opengauss

Enables interaction with openGauss databases through multiple transport methods (Stdio, SSE, Streamable-Http). Supports database operations and queries with configurable connection parameters.

TimeChimp MCP Server

Enables interaction with the TimeChimp API v2 to manage projects, time entries, expenses, and invoices through natural language. It supports full CRUD operations across all major TimeChimp resources, including advanced OData query filtering and pagination.

optionslab

Options analytics MCP server providing 40+ tools for options chain data, position valuation, Greeks, charts, and volatility analysis.

Rootstock MCP Server

A backend service that enables seamless interaction with the Rootstock blockchain using the Model Context Protocol, providing standardized APIs for querying, transacting, and managing assets on Rootstock.

TechMCP - PSG College of Technology MCP Server

Enables AI assistants to access PSG College of Technology e-campus portal data including CA marks, attendance records, timetable schedules, and course information through natural language queries.

MockMCP

Hosted MCP endpoint that returns realistic fake data for prototyping agents. Paste one URL into Claude Code, Cursor, or Claude Desktop — 12 pre-built tools covering users, products, orders, events, email, and knowledge base search. No signup, no config, no auth. Built for developers who want to prototype agent workflows before wiring up a real backend.

Nearest Tailwind Colors

Finds the closest Tailwind CSS palette colors to any given CSS color value. Supports multiple color spaces and customizable result filtering to help match designs to Tailwind's color system.

Sora MCP Server

Integrates with OpenAI's Sora 2 API to generate, remix, and manage AI-generated videos from text prompts. Supports video creation, status monitoring, downloading, and remixing through natural language commands.

CozoDB Memory MCP Server

Local-first memory for Claude & AI agents with hybrid search, Graph-RAG, and time-travel, runs entirely on your machine.

Rockfish MCP Server

Enables interaction with the Rockfish AI platform for synthetic data generation, dataset management, and ML workflow orchestration through tools like TabGAN training and Manta analytics.

mcp-scryfall

Provides access to Magic: The Gathering card database, enabling listing of sets and expansions.

MCP Chat with Claude

Okay, here's a TypeScript example demonstrating a web application (acting as the host) connecting to a Node.js MCP (Microcontroller Platform) server. This example focuses on the core communication setup. You'll need to adapt it based on the specific MCP protocol and data you're exchanging. **Conceptual Overview** 1. **Web App (Host - TypeScript/JavaScript):** * Uses WebSockets to establish a persistent connection with the MCP server. * Sends commands/requests to the MCP server. * Receives data/responses from the MCP server. * Updates the UI based on the received data. 2. **MCP Server (Node.js):** * Listens for WebSocket connections from the web app. * Receives commands/requests. * Processes the commands (potentially interacting with hardware). * Sends data/responses back to the web app. **Example Code** **1. MCP Server (Node.js - `mcp-server.ts`)** ```typescript // mcp-server.ts import WebSocket, { WebSocketServer } from 'ws'; const wss = new WebSocketServer({ port: 8080 }); // Choose your port wss.on('connection', ws => { console.log('Client connected'); ws.on('message', message => { try { const data = JSON.parse(message.toString()); // Assuming JSON format console.log('Received:', data); // **Process the received message here based on your MCP protocol** // Example: if (data.command === 'getSensorData') { // Simulate sensor data const sensorValue = Math.random() * 100; const response = { type: 'sensorData', value: sensorValue }; ws.send(JSON.stringify(response)); } else if (data.command === 'setLed') { // Simulate setting an LED console.log(`Setting LED to: ${data.state}`); const response = { type: 'ledStatus', state: data.state }; ws.send(JSON.stringify(response)); } else { console.log("Unknown command"); ws.send(JSON.stringify({type: 'error', message: 'Unknown command'})); } } catch (error) { console.error('Error parsing message:', error); ws.send(JSON.stringify({ type: 'error', message: 'Invalid JSON' })); } }); ws.on('close', () => { console.log('Client disconnected'); }); ws.on('error', error => { console.error('WebSocket error:', error); }); // Send a welcome message ws.send(JSON.stringify({ type: 'status', message: 'Connected to MCP Server' })); }); console.log('MCP Server started on port 8080'); ``` **To run the server:** 1. Make sure you have Node.js and npm installed. 2. Create a new directory for your project. 3. Inside the directory, run: `npm init -y` 4. Install the `ws` package: `npm install ws --save` 5. Install `typescript`: `npm install typescript --save-dev` 6. Create a `tsconfig.json` file: `npx tsc --init` (adjust settings as needed) 7. Place the `mcp-server.ts` file in the directory. 8. Compile the TypeScript: `npx tsc` 9. Run the server: `node mcp-server.js` (or `node dist/mcp-server.js` if you configured a `dist` output directory in `tsconfig.json`) **2. Web App (Host - TypeScript/HTML/JavaScript)** * **HTML (`index.html`):** ```html <!DOCTYPE html> <html> <head> <title>MCP Host</title> </head> <body> <h1>MCP Host</h1> <button id="getSensorData">Get Sensor Data</button> <p>Sensor Value: <span id="sensorValue"></span></p> <button id="ledOn">LED On</button> <button id="ledOff">LED Off</button> <p>LED Status: <span id="ledStatus"></span></p> <script src="app.js"></script> </body> </html> ``` * **TypeScript (`app.ts`):** ```typescript // app.ts const socket = new WebSocket('ws://localhost:8080'); // Replace with your server address socket.addEventListener('open', event => { console.log('Connected to MCP Server'); }); socket.addEventListener('message', event => { try { const data = JSON.parse(event.data); console.log('Received:', data); if (data.type === 'status') { console.log('Status:', data.message); } else if (data.type === 'sensorData') { const sensorValueElement = document.getElementById('sensorValue'); if (sensorValueElement) { sensorValueElement.textContent = data.value.toFixed(2); } } else if (data.type === 'ledStatus') { const ledStatusElement = document.getElementById('ledStatus'); if (ledStatusElement) { ledStatusElement.textContent = data.state ? 'On' : 'Off'; } } else if (data.type === 'error') { console.error('Error:', data.message); alert(`Error from server: ${data.message}`); } } catch (error) { console.error('Error parsing message:', error); } }); socket.addEventListener('close', event => { console.log('Disconnected from MCP Server'); }); socket.addEventListener('error', event => { console.error('WebSocket error:', event); }); // Button event listeners document.getElementById('getSensorData')?.addEventListener('click', () => { socket.send(JSON.stringify({ command: 'getSensorData' })); }); document.getElementById('ledOn')?.addEventListener('click', () => { socket.send(JSON.stringify({ command: 'setLed', state: true })); }); document.getElementById('ledOff')?.addEventListener('click', () => { socket.send(JSON.stringify({ command: 'setLed', state: false })); }); ``` **To run the web app:** 1. Create a directory for your web app files. 2. Place `index.html` and `app.ts` in the directory. 3. Compile the TypeScript: `npx tsc` 4. This will create an `app.js` file. 5. Open `index.html` in your web browser. You might need to serve it using a simple web server (e.g., using `npx serve` or `python -m http.server`). **Explanation and Key Points** * **WebSockets:** WebSockets provide a full-duplex communication channel over a single TCP connection. This is ideal for real-time data exchange between the web app and the MCP server. * **JSON:** The example uses JSON (JavaScript Object Notation) for message formatting. This is a common and easy-to-parse format for data exchange. You can adapt this to other formats if needed. * **Error Handling:** The code includes basic error handling for WebSocket events and JSON parsing. Robust error handling is crucial in real-world applications. * **MCP Protocol:** The most important part is defining your MCP protocol. This is the set of commands and data formats that the web app and MCP server will use to communicate. The example uses simple `command` and `type` fields to illustrate this. You'll need to design a protocol that meets the needs of your specific application. * **TypeScript Compilation:** The TypeScript code needs to be compiled into JavaScript before it can be run in the browser. The `tsc` command performs this compilation. * **Server Address:** Make sure the WebSocket URL in the web app (`ws://localhost:8080`) matches the address and port where your MCP server is listening. * **Security:** For production environments, consider using secure WebSockets (WSS) with TLS/SSL encryption. * **State Management:** In a more complex application, you'll likely need to manage the state of the connection and the data being exchanged. Consider using a state management library like Redux or Zustand for larger applications. * **UI Updates:** The example updates the HTML elements with the data received from the server. You'll need to adapt this to your specific UI requirements. **How to Adapt This Example** 1. **Define Your MCP Protocol:** This is the most important step. Determine the commands the web app can send to the MCP server and the data formats the server will use to respond. Consider things like: * Sensor data requests * Actuator control commands (e.g., turning LEDs on/off, controlling motors) * Configuration settings * Error reporting 2. **Implement MCP Server Logic:** Modify the MCP server code to handle the commands defined in your protocol. This might involve interacting with hardware (e.g., reading sensor values, controlling actuators). 3. **Implement Web App Logic:** Modify the web app code to send the appropriate commands to the MCP server and to handle the data received from the server. Update the UI accordingly. 4. **Error Handling:** Add more robust error handling to both the web app and the MCP server. 5. **Security:** Use secure WebSockets (WSS) for production environments. This example provides a basic foundation for building a web app that communicates with an MCP server. Remember to adapt it to your specific needs and to design a well-defined MCP protocol.

Google Chat MCP Server

Enables interaction with Google Chat via MCP using the internal Dynamite API, allowing listing spaces, reading and sending messages, and managing DMs. No Google Cloud Console setup required.

Data Science AI MCP

Data Science AI - MCP server providing AI-powered tools and automation by MEOK AI Labs