Discover Awesome MCP Servers

Outsource MCP

An MCP server that enables AI applications to access 20+ model providers (including OpenAI, Anthropic, Google) through a unified interface for text and image generation.

Charles MCP Server

Integrates Charles Proxy with MCP clients to provide real-time and historical network traffic capture and structured analysis. It features a summary-first approach that filters noise and desensitizes data for efficient, low-token agent debugging and monitoring.

mcp-server-markdown

MCP server for markdown files — search, extract sections, list headings, find code blocks across docs.

Clickzetta MCP Server

Sebuah server Protokol Konteks Model yang memungkinkan interaksi database dengan Clickzetta, memungkinkan pengguna untuk menjalankan kueri SQL, mengelola tabel, dan memelihara memo wawasan data yang diperbarui secara dinamis.

proxypin-mcp

Enables AI to analyze real-time HTTP(S) traffic captured by ProxyPin, with tools to browse, search, and inspect requests and responses, as well as access saved history sessions.

Redfish MCP Server

Enables interaction with Redfish-compliant BMC devices for server management, firmware updates, and hardware monitoring through session-based authentication and standardized API endpoints.

Remote MCP Server Authless

A tool that deploys an authentication-free Model Context Protocol server on Cloudflare Workers, allowing you to create and access custom AI tools from the Cloudflare AI Playground or Claude Desktop.

CODESYS MCP Server

Enables CODESYS development assistance via MCP, including curated guidance, Structured Text writing help, local PDF search, and live official documentation lookup.

Strudel MCP Server

Enables AI assistants to work with Strudel live coding patterns for music creation, including parsing mini notation, generating rhythmic patterns, accessing music theory (scales/chords), and applying pattern transformations.

Airbnb MCP Server

Memungkinkan pencarian daftar Airbnb dan pengambilan informasi akomodasi terperinci dengan tautan langsung ke halaman Airbnb.

ChurnFlow MCP Server

An ADHD-friendly productivity system that uses AI to provide frictionless capture of tasks and ideas through natural language input, with automatic context detection and intelligent routing to appropriate project trackers. Eliminates cognitive overhead by working with ADHD thinking patterns rather than against them.

llmmcp

Provides real-time, up-to-date documentation for major LLM providers (OpenAI, Anthropic, Google Gemini) to prevent hallucinations and outdated code patterns in AI agents.

MCP Weather Server

Provides weather information using the US National Weather Service API, including active weather alerts for US states and location-specific forecasts based on latitude and longitude coordinates.

Amazon Ads MCP

Facilitate the management and automation of Amazon Sponsored Ads

Coreflux MCP Server

Menghubungkan Claude dan asisten AI yang kompatibel dengan MCP lainnya ke broker MQTT Coreflux, memungkinkan mereka untuk menemukan dan menjalankan perintah Coreflux untuk mengelola model, tindakan, aturan, dan rute melalui bahasa alami.

Cal Server

Kalkulator ekspresi matematika yang memproses ekspresi masukan pengguna dan mengembalikan hasil perhitungan, mendukung operasi dasar dan konstanta bawaan seperti PI dan E.

SousChef

Enables comprehensive Chef-to-Ansible migration for enterprise infrastructure with 34 tools across cookbook analysis, resource conversion, InSpec integration, secrets management, and AWX/AAP deployment configuration.

Query MCP

Memungkinkan akses IDE ke database Supabase dengan eksekusi kueri SQL, manajemen skema, operasi admin Auth, dan kontrol keamanan bawaan untuk mencegah tindakan destruktif yang tidak disengaja.

TaxJar MCP Server by CData

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for TaxJar (beta): https://www.cdata.com/download/download.aspx?sku=JTZK-V&type=beta

mpc-legifrance

MCP server covering French law via the PISTE platform: 62 tools wrapping the full Légifrance API (legislation, codes, Journal Officiel, jurisprudence…)

MCP-Server

A Flask-based MCP server with web GUI that provides utility tools for mathematical calculations, text analysis, string transformations, timestamps, and Fibonacci sequence generation.

CreateOS MCP

Deploy, manage, and scale applications directly from your AI assistant.

Git Workflow MCP Server

Enables AI assistants to interact with local Git repositories for operations like status, commits, branching, and diffs, plus GitHub API integration for managing pull requests when authenticated.

MCP Replicate FLUX

A Model Context Protocol server that generates images using Replicate's FLUX model and stores them in Cloudflare R2, allowing users to create images through simple prompts and retrieve accessible URLs.

mcp-task

Demo server MCP yang menunjukkan manajemen tugas.

HeroUI MCP Server

A high-quality, open-source Model Context Protocol (MCP) server that bridges AI systems and HeroUI, enabling intelligent assistance for developers working with HeroUI components.

spring-ai-playground

Spring AI Playground is a self-hosted web UI platform for building low-code tools and dynamically exposing them via built-in MCP server for AI agents.

Indian Stock Exchange API2 MCP Server

Enables access to comprehensive Indian stock market data from the NSE and BSE, including historical statistics, corporate actions, and IPO information. It also provides tools for mutual fund searches, analyst recommendations, and tracking market-active or trending stocks.

toyMCP To-Do List Server

Ini adalah contoh server sederhana yang mengimplementasikan API CRUD daftar To-Do menggunakan konsep Model Context Protocol (MCP), khususnya menggunakan JSON-RPC 2.0 melalui HTTP. Server ini menggunakan Node.js, Express, dan PostgreSQL (melalui Docker) untuk persistensi data.

MCP Server TypeScript Starter

Berikut adalah templat awal untuk membuat server Model Context Protocol (MCP) menggunakan TypeScript: ```typescript // Import necessary libraries (example: express for the server) import express, { Express, Request, Response } from 'express'; // Define the MCP request and response types (adjust based on your specific MCP) interface MCPRequest { // Define the structure of the request body here // Example: inputData: string; } interface MCPResponse { // Define the structure of the response body here // Example: result: string; status: string; } // Create the Express app const app: Express = express(); const port = process.env.PORT || 3000; // Middleware to parse JSON request bodies app.use(express.json()); // Define the MCP endpoint app.post('/mcp', (req: Request, res: Response) => { try { // 1. Validate the request body const requestBody: MCPRequest = req.body; if (!requestBody || !requestBody.inputData) { return res.status(400).json({ error: 'Invalid request body' }); } // 2. Process the request (This is where your model logic goes) // Replace this with your actual model processing code const input = requestBody.inputData; const processedResult = `Processed: ${input}`; // Example processing // 3. Construct the response const response: MCPResponse = { result: processedResult, status: 'success', }; // 4. Send the response res.json(response); } catch (error) { console.error('Error processing MCP request:', error); res.status(500).json({ error: 'Internal server error' }); } }); // Start the server app.listen(port, () => { console.log(`MCP server listening on port ${port}`); }); ``` **Explanation:** 1. **Import Libraries:** This section imports necessary libraries. The example uses `express` for creating a simple web server. You might need to install it: `npm install express @types/express` 2. **Define Request and Response Types:** `MCPRequest` and `MCPResponse` interfaces define the structure of the data being sent to and received from the server. **Crucially, you need to adapt these interfaces to match the specific requirements of your Model Context Protocol.** The example provides a simple `inputData` and `result` field, but your MCP will likely have more complex data structures. 3. **Create Express App:** This creates an instance of the Express application. 4. **Middleware:** `app.use(express.json())` is middleware that parses JSON request bodies. This allows you to easily access the data sent in the request. 5. **Define MCP Endpoint:** `app.post('/mcp', ...)` defines the endpoint that will handle MCP requests. It's a `POST` request because you're typically sending data to the server. - **Request Validation:** The code first validates the request body to ensure it contains the required data. This is important for preventing errors and security vulnerabilities. - **Process the Request:** This is the **most important part** where you'll integrate your model logic. The example provides a placeholder that simply prepends "Processed: " to the input data. **You need to replace this with the actual code that interacts with your model.** This might involve loading a model, running inference, and formatting the results. - **Construct the Response:** The code constructs the `MCPResponse` object with the results of the processing. - **Send the Response:** The code sends the response back to the client as JSON. 6. **Error Handling:** The `try...catch` block handles potential errors during request processing and sends a 500 Internal Server Error response. Proper error handling is crucial for a robust server. 7. **Start the Server:** `app.listen(port, ...)` starts the server and listens for incoming requests on the specified port. **How to Use:** 1. **Install Dependencies:** ```bash npm install express @types/express npm install -D typescript ts-node nodemon # For development npm install -g ts-node # Optional: for running directly with ts-node ``` 2. **Create a `tsconfig.json` file:** This file configures the TypeScript compiler. A basic example: ```json { "compilerOptions": { "target": "es6", "module": "commonjs", "outDir": "./dist", "esModuleInterop": true, "strict": true, "moduleResolution": "node", "sourceMap": true }, "include": ["src/**/*"], "exclude": ["node_modules"] } ``` 3. **Save the code:** Save the code above as `src/index.ts` (or any other name you prefer). 4. **Compile the code:** ```bash tsc ``` This will compile the TypeScript code into JavaScript files in the `dist` directory. 5. **Run the server:** ```bash node dist/index.js ``` Or, if you have `ts-node` installed globally: ```bash ts-node src/index.ts ``` For development, use `nodemon` to automatically restart the server on code changes: ```bash nodemon --exec ts-node src/index.ts ``` 6. **Test the server:** You can use `curl`, `Postman`, or any other HTTP client to send a `POST` request to `http://localhost:3000/mcp` with a JSON body like this: ```json { "inputData": "Hello, world!" } ``` **Key Considerations and Next Steps:** * **Model Integration:** The most important step is to replace the placeholder processing logic with your actual model integration code. This will depend on the type of model you're using (e.g., TensorFlow, PyTorch, scikit-learn) and how you want to deploy it. You might need to load the model from a file, connect to a remote model server, or use a cloud-based model deployment service. * **Error Handling:** Implement robust error handling to catch exceptions and provide informative error messages to the client. Consider logging errors for debugging purposes. * **Security:** Implement appropriate security measures to protect your server from unauthorized access and malicious attacks. This might include authentication, authorization, input validation, and rate limiting. * **Scalability:** If you expect a high volume of requests, consider using a load balancer and scaling your server across multiple instances. * **Configuration:** Use environment variables to configure the server, such as the port number, model path, and API keys. * **Logging:** Implement logging to track requests, errors, and other important events. This can be helpful for debugging and monitoring the server. * **Testing:** Write unit tests and integration tests to ensure that your server is working correctly. * **Deployment:** Choose a deployment platform (e.g., AWS, Google Cloud, Azure, Heroku) and deploy your server. * **Documentation:** Document your API and how to use it. This template provides a solid foundation for building an MCP server using TypeScript. Remember to adapt it to your specific needs and requirements. Good luck!