Discover Awesome MCP Servers

ClickUp MCP Server

Mirror of

ZIP MCP Server

Uma ferramenta MCP que fornece à IA a capacidade de comprimir e descomprimir arquivos locais.

Fantasy Premier League MCP Server

Fantasy Premier League MCP Server

MCPHubs - Model Context Protocol Projects Hub

MCPHubs é um site que apresenta projetos relacionados ao Protocolo de Contexto de Modelo (MCP) da Anthropic.

Hologres MCP Server

A universal interface that enables AI Agents to communicate with Hologres databases, allowing them to retrieve database metadata and execute SQL operations.

Airtable MCP Server Setup

Airtable MCP server configuration and documentation

MCP Serverless

Serverless implementation of the Model Context Protocol (MCP)

Overview

Servidor MCP Alphavantage

Chronicle SecOps MCP Server

Um servidor MCP para interagir com o pacote Chronicle Security Operations do Google, permitindo que os usuários pesquisem eventos de segurança, recebam alertas, consultem entidades, listem regras de segurança e recuperem correspondências de IoC (Indicadores de Comprometimento).

SEO Tools MCP Server

Permite que LLMs interajam com DataForSEO e outras APIs de SEO através de linguagem natural, possibilitando pesquisa de palavras-chave, análise de SERPs, análise de backlinks e tarefas de SEO local.

Booking System (Fixed)

Sistema de reservas fixo com integração ao Google Calendar, confirmações por e-mail e integração ao Servidor MCP.

search-fetch-server MCP Server

Mirror of

Github MCP Server

Mirror of

Dockerized GitHub MCP Server

this is mcp servers in local

Ansible Tower MCP Server

MCP Server for Ansible Tower

Rootly MCP Server

Gerencie incidentes diretamente do seu IDE. Um servidor MCP que permite extrair incidentes e seus metadados associados usando a API Rootly.

Google Tasks MCP Server

Um servidor de Protocolo de Contexto de Modelo que conecta Claude com o Google Tasks, permitindo que os usuários gerenciem listas de tarefas e tarefas diretamente através da interface do Claude.

🤖 MCPServe by @ryaneggz

Simple MCP Server w/ Shell Exec. Connect to Local via Ngrok, or Host Ubuntu24 Container via Docker

YouTube transcript extractor for your LLM

Here are a few options for an MCP (presumably you mean a server or application that can be deployed on a server) that downloads YouTube transcripts, along with considerations for each: **1. Python-based Solution (using `youtube-transcript-api` and a web framework like Flask or FastAPI):** * **Concept:** This is a very common and flexible approach. You'd use the `youtube-transcript-api` library to fetch the transcripts and a web framework to create an API endpoint that accepts a YouTube video ID and returns the transcript. * **Components:** * **Python:** The core language. * **`youtube-transcript-api`:** A Python library specifically designed to retrieve YouTube transcripts. Install with `pip install youtube-transcript-api`. * **Flask or FastAPI:** A lightweight Python web framework. Flask is simpler to start with, FastAPI is generally faster and has automatic API documentation. Install with `pip install flask` or `pip install fastapi uvicorn`. * **(Optional) Celery/Redis:** For asynchronous task processing. If you expect a high volume of requests, you don't want the web server to block while waiting for the transcript to download. Celery is a task queue, and Redis is often used as its broker. * **(Optional) Database (e.g., PostgreSQL, MySQL, SQLite):** To store the transcripts for later retrieval. This is useful if you want to avoid repeatedly downloading the same transcripts. * **Example (Flask - very basic):** ```python from flask import Flask, request, jsonify from youtube_transcript_api import YouTubeTranscriptApi app = Flask(__name__) @app.route('/transcript', methods=['GET']) def get_transcript(): video_id = request.args.get('video_id') if not video_id: return jsonify({'error': 'video_id parameter is required'}), 400 try: transcript = YouTubeTranscriptApi.get_transcript(video_id) return jsonify(transcript) except Exception as e: return jsonify({'error': str(e)}), 500 if __name__ == '__main__': app.run(debug=True) ``` **To run this:** 1. Save as `app.py`. 2. `pip install flask youtube-transcript-api` 3. `python app.py` 4. Access in your browser or with `curl`: `http://127.0.0.1:5000/transcript?video_id=YOUR_YOUTUBE_VIDEO_ID` * **Advantages:** * Highly customizable. * Relatively easy to set up. * Python has excellent libraries for web development and data processing. * Can be easily deployed to various platforms (e.g., Heroku, AWS, Google Cloud). * **Disadvantages:** * Requires some programming knowledge. * Needs more setup than a pre-built solution. * Error handling and rate limiting need to be implemented carefully. YouTube might block your IP if you make too many requests too quickly. * **Important Considerations:** * **Error Handling:** The example above has basic error handling, but you'll want to handle cases where the video doesn't exist, has disabled transcripts, or the `youtube-transcript-api` encounters an error. * **Rate Limiting:** Implement a mechanism to limit the number of requests per IP address or user to avoid being blocked by YouTube. Consider using a library like `Flask-Limiter` or `FastAPI's Depends` system. * **Asynchronous Processing:** Use Celery or a similar task queue to handle transcript downloads in the background, especially if you expect a high volume of requests. * **Caching:** Cache the transcripts in a database or in-memory cache (like Redis) to avoid repeatedly downloading the same transcripts. * **Deployment:** Choose a deployment platform (e.g., Heroku, AWS, Google Cloud) and configure your server accordingly. Use a WSGI server like Gunicorn or uWSGI for production deployments. **2. Node.js-based Solution (using `youtube-transcript` and Express.js):** * **Concept:** Similar to the Python approach, but using JavaScript and Node.js. * **Components:** * **Node.js:** The JavaScript runtime. * **`youtube-transcript`:** A Node.js library for fetching YouTube transcripts. Install with `npm install youtube-transcript`. * **Express.js:** A popular Node.js web framework. Install with `npm install express`. * **(Optional) Bull/Redis:** For asynchronous task processing (similar to Celery/Redis in Python). * **(Optional) Database (e.g., MongoDB, PostgreSQL):** To store the transcripts. * **Example (Express.js - very basic):** ```javascript const express = require('express'); const { getTranscript } = require('youtube-transcript'); const app = express(); const port = 3000; app.get('/transcript', async (req, res) => { const videoId = req.query.video_id; if (!videoId) { return res.status(400).json({ error: 'video_id parameter is required' }); } try { const transcript = await getTranscript(videoId); return res.json(transcript); } catch (error) { console.error(error); return res.status(500).json({ error: error.message }); } }); app.listen(port, () => { console.log(`Server listening at http://localhost:${port}`); }); ``` **To run this:** 1. Save as `app.js`. 2. `npm install express youtube-transcript` 3. `node app.js` 4. Access in your browser or with `curl`: `http://localhost:3000/transcript?video_id=YOUR_YOUTUBE_VIDEO_ID` * **Advantages:** * Similar advantages to the Python approach. * JavaScript is widely used, so you might already be familiar with it. * Node.js is known for its performance in I/O-bound tasks. * **Disadvantages:** * Requires JavaScript and Node.js knowledge. * Similar setup and considerations as the Python approach (error handling, rate limiting, etc.). **3. Pre-built Solutions/Services (Less Common for this specific task):** * While there aren't many *dedicated* pre-built MCP servers specifically for *just* downloading YouTube transcripts, you might find services that offer transcript extraction as part of a larger suite of video analysis tools. These are often paid services. Examples might include: * **Video Intelligence APIs (Google Cloud Video Intelligence API, AWS Rekognition Video):** These APIs can extract transcripts, but they are more general-purpose and might be overkill (and more expensive) if you only need transcripts. * **Third-party video analysis platforms:** Some platforms offer transcript extraction as a feature. You'd need to research specific platforms to see if they meet your needs. * **Advantages:** * Minimal setup. * Often include additional features (e.g., sentiment analysis, object detection). * Managed infrastructure. * **Disadvantages:** * Can be expensive. * Less control over the implementation. * Might not be as customizable. * Potential privacy concerns if you're dealing with sensitive data. **Which Option to Choose:** * **For maximum flexibility and control:** The Python or Node.js approach is best. Choose the language you're most comfortable with. * **For a quick and easy solution (if you don't need much customization):** Look for a pre-built service, but be prepared to pay for it. Carefully evaluate the service's features and pricing. * **For learning and experimentation:** The Python or Node.js approach is a great way to learn about web development, APIs, and task queues. **Key Considerations for All Options:** * **YouTube's Terms of Service:** Make sure your usage complies with YouTube's Terms of Service. Avoid scraping the website directly; use the official APIs or libraries like `youtube-transcript-api` and `youtube-transcript`. * **API Keys/Authentication:** Some services might require API keys or authentication. Store these securely. * **Scalability:** If you expect a high volume of requests, design your server to be scalable. Use asynchronous processing, caching, and load balancing. * **Legal and Ethical Considerations:** Be mindful of copyright and privacy issues when dealing with transcripts. **In summary, the Python or Node.js approach using the `youtube-transcript-api` or `youtube-transcript` library, respectively, and a web framework like Flask, FastAPI, or Express.js is generally the most practical and flexible solution for building an MCP server that downloads YouTube transcripts.** Remember to implement proper error handling, rate limiting, and caching.

MCP-SSE3

created from MCP server demo

Playwright MCP

O servidor MCP do Playwright permite a geração de testes do Playwright orientada por IA, permitindo a interação com páginas da web e a inspeção de elementos. Integrado com IDEs como o Cursor, ele fornece contexto em tempo real para aprimorar a precisão e a eficiência dos testes.

MCP-Wikipedia-API-Server

Um servidor FastAPI-MCP que busca resumos da Wikipedia para assistentes de IA, implementado usando Google Colab e Ngrok.

Superset MCP Integration

Servidor MCP que permite que agentes de IA se conectem e controlem instâncias do Apache Superset programaticamente, permitindo que os usuários gerenciem painéis, gráficos, bancos de dados, conjuntos de dados e executem consultas SQL por meio de interações em linguagem natural.

Weather MCP Server

Okay, here's an example of creating an MCP (Minecraft Coder Pack) server setup. Keep in mind that MCP itself doesn't create a *server* in the traditional sense. MCP is a tool for decompiling, deobfuscating, and re-compiling the Minecraft client and server code. You use it to *modify* the server code. What I'll show you is how to set up MCP, decompile the server, and then the basic steps to build a modified server. **Important Considerations:** * **Minecraft Version:** MCP is version-specific. You *must* use the correct MCP version for the Minecraft version you want to modify. Using the wrong version will lead to errors. Find the appropriate MCP version on the MCP website or forums. * **Legal:** Modifying and distributing modified Minecraft code is subject to Mojang's terms of service. Be sure you understand and comply with them. * **Complexity:** This is a complex process. Be prepared to troubleshoot and learn. Basic Java knowledge is essential. **Steps:** 1. **Download MCP:** * Go to a trusted source for MCP (e.g., the official MCP forums or a reputable modding community). Download the MCP package for the Minecraft version you want to work with. For example, you might download `mcp940.zip` for Minecraft 1.9.4. (The exact filename will vary.) 2. **Extract MCP:** * Extract the downloaded ZIP file to a directory on your computer. A common location is `C:\mcp` (on Windows) or `/home/user/mcp` (on Linux). Avoid spaces in the path. 3. **Download the Minecraft Server JAR:** * Download the official Minecraft server JAR file from Mojang's website: [https://www.minecraft.net/en-us/download/server](https://www.minecraft.net/en-us/download/server) * Place the server JAR file (e.g., `server.jar`) into the `jars` directory within your MCP directory. Rename it to `minecraft_server.X.X.X.jar` where `X.X.X` is the Minecraft version (e.g., `minecraft_server.1.19.4.jar`). 4. **Configure MCP (Optional, but Recommended):** * **`conf/mcp.cfg`:** Open the `conf/mcp.cfg` file in a text editor. This file contains configuration options for MCP. You might want to adjust the following: * `MCP_LOC`: This should point to the root directory of your MCP installation. It's usually correct by default. * `PATCH`: Set this to `True` if you plan to create patches for your modifications. * `REOBFUSCATE`: Set this to `True` if you want to reobfuscate the code after making changes. This is generally not needed for simple modifications. 5. **Decompile the Server:** * Open a command prompt or terminal. * Navigate to your MCP directory using the `cd` command. For example: ```bash cd C:\mcp # Windows cd /home/user/mcp # Linux ``` * Run the decompilation command: ```bash ./decompile.sh # Linux/macOS ./decompile.bat # Windows ``` This process will take some time. MCP will download necessary files, decompile the Minecraft server JAR, and create source code files. Pay attention to the output for any errors. 6. **Set up Eclipse (or your IDE):** * MCP is designed to work well with Eclipse. If you don't have Eclipse, download and install it. * In Eclipse, create a new Java project. * Set the project's source folder to `src/minecraft_server`. This is where the decompiled server source code is located. * Add the libraries from the `lib` directory in your MCP folder to your project's build path. These libraries are necessary for compiling the Minecraft code. 7. **Modify the Server Code:** * Now you can browse and modify the decompiled server code in Eclipse. The code is organized into packages and classes. For example, you might find the server's main class in `net.minecraft.server`. * **Example Modification:** Let's say you want to change the server's MOTD (Message of the Day). You would need to find the class responsible for setting the MOTD (this requires some code exploration). Then, you would modify the code to set a different MOTD. 8. **Recompile the Server:** * After making your changes, recompile the server code using the following command in your MCP directory: ```bash ./recompile.sh # Linux/macOS ./recompile.bat # Windows ``` This will compile the modified source code into class files. 9. **Reobfuscate (Optional, Usually Not Needed):** * If you set `REOBFUSCATE = True` in `mcp.cfg`, you can reobfuscate the code after recompiling. This makes the code harder to understand, but it's generally not necessary for simple modifications. ```bash ./reobfuscate.sh # Linux/macOS ./reobfuscate.bat # Windows ``` 10. **Create the Modified Server JAR:** * Use the `createMcpServer.sh` or `createMcpServer.bat` script to create the final server JAR file. ```bash ./createMcpServer.sh # Linux/macOS ./createMcpServer.bat # Windows ``` * This script will create a new JAR file in the `jars` directory, typically named something like `minecraft_server_modded.jar`. 11. **Run the Modified Server:** * Copy the `minecraft_server_modded.jar` file to a new directory where you want to run your server. * Create a `start.bat` (Windows) or `start.sh` (Linux/macOS) file to start the server. Here's an example: **`start.bat` (Windows):** ```batch java -Xmx2G -Xms2G -jar minecraft_server_modded.jar nogui pause ``` **`start.sh` (Linux/macOS):** ```bash #!/bin/bash java -Xmx2G -Xms2G -jar minecraft_server_modded.jar nogui ``` Make the `start.sh` file executable: `chmod +x start.sh` * Run the `start.bat` or `start.sh` file to start your modified server. **Troubleshooting:** * **Errors during decompilation:** Make sure you have the correct MCP version for your Minecraft version. Check the MCP forums for known issues. * **Compilation errors:** Check your code for syntax errors. Make sure you have added the necessary libraries to your project's build path. * **Server crashes:** Check the server logs for error messages. The logs are located in the server directory. **Important Notes:** * This is a simplified example. Modifying Minecraft code can be complex, and you may need to learn more about Java and the Minecraft code structure. * Always back up your files before making any changes. * Be careful when distributing modified Minecraft code. Make sure you comply with Mojang's terms of service. This detailed explanation should give you a good starting point for creating a modified Minecraft server using MCP. Remember to consult the MCP documentation and community forums for more information and support. Good luck!

Alpha Vantage MCP Server 📈

Um servidor MCP que fornece integração de dados financeiros em tempo real com a API da Alpha Vantage, permitindo o acesso a dados do mercado de ações, preços de criptomoedas, taxas de câmbio e indicadores técnicos.

Untappd Model Context Protocol Server

Um servidor de Protocolo de Contexto de Modelo que permite ao Claude consultar a API do banco de dados de cervejas Untappd para pesquisar cervejas e recuperar informações detalhadas sobre elas.