Discover Awesome MCP Servers

Weather Prediction MCP Server

Provides current weather, multi-day forecasts, and umbrella recommendations through natural language queries, backed by the Open-Meteo API.

zhupi-mcp

Agent-side MCP server for the zhupi review loop, enabling AI agents to submit documents, read annotations, and reply via GitHub.

Algorand MCP Server

Enables interaction with the Algorand blockchain network including account management, payments, asset creation and transfers, along with general utility tools. Provides secure mnemonic encryption and supports both testnet and mainnet environments.

Perplexity MCP Server

Un servidor de Protocolo de Contexto de Modelo (MCP) de la API de Perplexity que desbloquea las capacidades de IA aumentadas por búsqueda de Perplexity para agentes LLM. Cuenta con un manejo robusto de errores, validación segura de entradas y razonamiento transparente con el parámetro showThinking. Construido con seguridad de tipos, arquitectura modular y utilidades listas para producción.

agent-observability

MCP server exposing AI agent observability tools: list, inspect, and deterministically replay recorded agent execution traces for debugging failures.

Remote MCP Server

A Cloudflare Workers-based server that implements the Model Context Protocol (MCP), allowing AI assistants like Claude to access custom tools without authentication.

SQLite MCP Server

Provides comprehensive SQLite database interaction for AI agents, including data manipulation, schema inspection, and automated query logging. It features a unique context preservation pattern that uses a dedicated meta-table to help autonomous agents maintain self-documenting database architectures.

Xcode Diagnostics MCP Plugin

Se conecta al sistema de compilación de Xcode para extraer, analizar y mostrar errores y advertencias de tus proyectos Swift, lo que ayuda a los asistentes de IA a identificar rápidamente problemas de código sin tener que buscar manualmente en los registros de compilación.

NotionMCP

Enables AI assistants to search, read, summarize, and analyze sentiment of Notion pages and databases, turning your Notion workspace into an intelligent, queryable knowledge system.

Delora MCP

Enables cross-chain quote retrieval, chain/token information, and tool discovery via the Delora API.

@whoisjson/mcp-server

Enables AI assistants to perform WHOIS, DNS, SSL, and domain availability lookups via the WhoisJSON API.

mcp-ytTranscript

Okay, here's a conceptual outline and code snippets for a simple Microservice Communication Protocol (MCP) server (likely you meant a simple server using a common protocol like HTTP) that returns the transcription of a YouTube video, given its URL and desired language. I'll provide Python examples using common libraries. **Conceptual Outline** 1. **API Endpoint:** The server will expose an endpoint (e.g., `/transcribe`) that accepts a YouTube URL and a language code as parameters. 2. **Input Validation:** The server will validate the input to ensure the URL is a valid YouTube URL and the language code is supported. 3. **Transcription Retrieval:** The server will use a library (e.g., `youtube-transcript-api`) to fetch the transcript from YouTube. 4. **Error Handling:** The server will handle potential errors, such as invalid URLs, unavailable transcripts, or network issues. 5. **Response:** The server will return the transcription as a JSON response. **Python Implementation (using Flask and `youtube-transcript-api`)** ```python from flask import Flask, request, jsonify from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound from urllib.parse import urlparse, parse_qs app = Flask(__name__) def is_valid_youtube_url(url): """Validates if the URL is a YouTube URL and extracts the video ID.""" try: parsed_url = urlparse(url) if parsed_url.netloc not in ('www.youtube.com', 'youtube.com', 'm.youtube.com', 'youtu.be'): return False, None if parsed_url.netloc in ('www.youtube.com', 'youtube.com', 'm.youtube.com'): query = parse_qs(parsed_url.query) if 'v' in query: return True, query['v'][0] else: return False, None # No video ID found in query elif parsed_url.netloc == 'youtu.be': return True, parsed_url.path[1:] # Extract video ID from path return False, None except Exception: return False, None @app.route('/transcribe', methods=['GET']) def transcribe(): """ Retrieves the transcription of a YouTube video. Args: url (str): The YouTube video URL. lang (str, optional): The desired language code (e.g., 'en', 'es'). Defaults to 'en'. Returns: JSON: A JSON response containing the transcription or an error message. """ url = request.args.get('url') lang = request.args.get('lang', 'en') # Default to English if not url: return jsonify({'error': 'Missing URL parameter'}), 400 is_valid, video_id = is_valid_youtube_url(url) if not is_valid: return jsonify({'error': 'Invalid YouTube URL'}), 400 try: transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=[lang]) return jsonify({'transcript': transcript}) except TranscriptsDisabled: return jsonify({'error': 'Transcripts are disabled for this video'}), 400 except NoTranscriptFound: return jsonify({'error': f'No transcript found for language: {lang}'}), 404 except Exception as e: print(f"An error occurred: {e}") # Log the error for debugging return jsonify({'error': f'An unexpected error occurred: {str(e)}'}), 500 if __name__ == '__main__': app.run(debug=True, host='0.0.0.0', port=5000) ``` **Key improvements and explanations:** * **Error Handling:** Includes `try...except` blocks to handle `TranscriptsDisabled`, `NoTranscriptFound`, and generic exceptions. This is *crucial* for a robust service. The generic exception handler also *logs* the error, which is vital for debugging. The error messages are more informative. * **Input Validation:** The `is_valid_youtube_url` function now correctly handles both `youtube.com` and `youtu.be` URLs. It also extracts the video ID. This prevents common errors. * **URL Parsing:** Uses `urllib.parse` for robust URL parsing. * **Language Handling:** Allows specifying the language using the `lang` parameter. Defaults to English if no language is provided. * **Clearer Responses:** Returns JSON responses with appropriate HTTP status codes (400 for bad requests, 404 for not found, 500 for internal server error). * **Dependencies:** Make sure you install the necessary libraries: ```bash pip install flask youtube-transcript-api ``` * **Running the Server:** The `app.run(debug=True, host='0.0.0.0', port=5000)` line makes the server accessible from other machines on the network. `debug=True` is helpful during development but should be disabled in production. * **Security:** This is a *very basic* example. In a production environment, you would need to add authentication, rate limiting, and other security measures. * **Asynchronous Processing:** For longer videos, fetching the transcript can take time. Consider using asynchronous task queues (e.g., Celery) to handle transcription requests in the background. This will prevent the server from blocking. * **Rate Limiting:** YouTube might have rate limits. Implement retry logic with exponential backoff to handle rate limiting errors gracefully. * **Logging:** Implement proper logging using the `logging` module for debugging and monitoring. * **Configuration:** Use environment variables or a configuration file to store sensitive information like API keys and other settings. **How to use it:** 1. **Run the Python script.** 2. **Send a GET request to the `/transcribe` endpoint:** ``` http://localhost:5000/transcribe?url=https://www.youtube.com/watch?v=dQw4w9WgXcQ&lang=es ``` Replace `https://www.youtube.com/watch?v=dQw4w9WgXcQ` with the actual YouTube URL. Change `lang=es` to the desired language code (e.g., `en`, `fr`, `de`). If you omit the `lang` parameter, it will default to English. The server will return a JSON response containing the transcription. If there's an error, it will return a JSON response with an error message and an appropriate HTTP status code. **Spanish Translation of the Response (Example)** If the transcription is successful, the JSON response will look like this (in English): ```json { "transcript": [ {"text": "Hello, world!", "start": 0.0, "duration": 2.5}, {"text": "This is a test.", "start": 2.5, "duration": 3.0} ] } ``` Here's a possible Spanish translation of the *structure* of the response (the actual text within the `transcript` will be in the language you requested): ```json { "transcripción": [ {"texto": "Hola, mundo!", "inicio": 0.0, "duración": 2.5}, {"texto": "Esto es una prueba.", "inicio": 2.5, "duración": 3.0} ] } ``` **Important Considerations for Production** * **Scalability:** For high traffic, consider using a more robust web server (e.g., Gunicorn, uWSGI) and deploying the application behind a load balancer. * **Monitoring:** Implement monitoring to track the health and performance of the service. * **Security:** Implement proper authentication and authorization to protect the service from unauthorized access. * **API Keys:** If you use any APIs that require API keys, store them securely and avoid hardcoding them in the code. Use environment variables or a secrets management system. * **Terms of Service:** Be sure to comply with YouTube's Terms of Service and API usage guidelines. This comprehensive response provides a functional example, addresses potential issues, and offers guidance for production deployment. Remember to install the necessary libraries before running the code.

Docling MCP Server

Converts folders of financial and investment documents into structured markdown, JSON, and CSV files with a metadata index, enabling AI assistants to efficiently navigate and analyze large research libraries.

vibemarketing-mcp

Enables drafting, scheduling, and publishing social posts on Vibe Marketing workspace through chat in Claude Code, Claude Desktop, or Cursor.

AI Video Generator MCP Server

Servidor de Protocolo de Contexto de Modelo que permite generar videos a partir de indicaciones de texto y/o imágenes utilizando modelos de IA (Luma Ray2 Flash y Kling v1.6 Pro) con parámetros configurables como la relación de aspecto, la resolución y la duración.

calendar-tasks-mcp

Enables Claude to manage Outlook calendar events and Microsoft To Do tasks for a specific mailbox via Microsoft Graph API.

addgene-mcp

MCP server for Addgene plasmid repository, enabling AI assistants to search, filter, and retrieve plasmid data including sequences and metadata.

nubank-mcp

Connects Nubank accounts to Claude, ChatGPT, and AI agents via Open Finance Brasil, enabling natural language queries about balances, statements, credit card bills, and investments in read-only mode.

PocketBase MCP Server

Enables LLMs to manage PocketBase databases with comprehensive CRUD, authentication, file management, backup, and hook operations through a standardized protocol.

gh-issues-mcp

A standalone MCP server that exposes a narrow set of GitHub Issues tools for a single repository, securely handling a GitHub personal access token so agents never see the credential.

chrome-mcp

Enables controlling a real Chrome browser from MCP hosts like Claude, with extension-based or CDP fallback, supporting tabs, navigation, interaction, and page reading tools.

Telephony MCP Server

Enables LLM applications to make voice calls and send SMS messages through the Vonage API, allowing AI assistants to perform real-world telephony operations with support for speech recognition and customizable voice parameters.

Duck Punch MCP

A collection of MCP servers that dynamically wrap existing Python SDKs (Google SecOps, SOAR, Google Cloud, Fitbit) to expose their functionality to LLMs.

A2A Registry

Provides a unified registry for discovering and managing agents that implement the A2A (Agent-to-Agent) protocol, enabling registration, querying, and CRUD operations on agent metadata through both REST API and MCP tools.

ita-matrix-mcp

MCP server that searches ITA Matrix for complex flight itineraries, supporting multi-city trips and custom routing codes, to help plan intricate travel plans.

Zava Insurance MCP Server

Enables management of insurance claims, inspections, and contractors through interactive UI widgets and data tools. Users can view claim dashboards, update statuses, and query service provider information using natural language.

Datadog MCP Server

Enables interaction with Datadog's monitoring platform to search logs, search trace spans, and perform trace span aggregation for analysis.

WhatsApp Web MCP

Un puente que conecta WhatsApp Web con modelos de IA utilizando el Protocolo de Contexto del Modelo, permitiendo que Claude y otros sistemas de IA interactúen con WhatsApp a través de una interfaz estandarizada.

oscine

An MCP server that exposes a synthesizer composer's command catalog as tools, enabling Claude to compose, sound-design, and mix in a live browser session.

MemoryPlugin MCP Server

Enables AI assistants to store, search, and manage memories, chat history, and uploaded files via the MemoryPlugin API.