Discover Awesome MCP Servers

metabase-mcp-navi

A MCP server for Metabase that gives AI assistants direct access to dashboards, cards, and query execution.

Git Commit Message Generator MCP Server

An intelligent MCP server that automatically generates Conventional Commits style commit messages by analyzing git diffs using LLM providers like DeepSeek and Groq. It enables developers to maintain standardized version history through natural language interactions in supported MCP clients.

MCP Server

A server implementation of the Model Context Protocol that allows users to extend Claude's capabilities by creating custom tools that can be used within the Claude Desktop client.

Teleprompter

Enables storage and reuse of prompt templates with variable substitution for LLMs. Supports creating, searching, and retrieving prompt templates to avoid repeating complex instructions across conversations.

OpenProject MCP

An MCP server that lets local AI agents read and manage OpenProject project data through structured, guarded tools, with write operations requiring explicit confirmation.

MCP Server Deployment Demo

A demonstration MCP server that provides a simple addition tool for learning how to create and deploy servers following the Model-Context-Protocol specification. Serves as a basic example for developers getting started with MCP server development.

MCP Server for Awesome-llms-txt

Okay, I understand. You want me to create an MCP (presumably referring to a "Minimal, Complete, and Verifiable" example) server setup for the `SecretiveShell/Awesome-llms-txt` project, and to document the process directly within this conversation, using MCP resources. This is a bit abstract, as I don't have direct access to your file system or the `SecretiveShell/Awesome-llms-txt` project. Therefore, I'll provide a *conceptual* MCP, focusing on the core elements and assuming a basic understanding of Python and server setup. You'll need to adapt this to your specific environment and project structure. **Conceptual MCP: A Simple API Server for Serving Text from `Awesome-llms-txt`** This MCP will focus on: 1. **Loading Text Data:** How to load text data from a file (assuming `Awesome-llms-txt` contains text files). 2. **A Minimal API Endpoint:** A single API endpoint that returns the content of a specific text file. 3. **Basic Server Setup (using Flask):** A simple Flask server to host the API. 4. **Documentation within the Code:** Docstrings and comments to explain the code. **Code (Python with Flask):** ```python from flask import Flask, jsonify, abort import os app = Flask(__name__) # --- Configuration --- TEXT_DIRECTORY = "path/to/your/Awesome-llms-txt/text_files" # Replace with the actual path ALLOWED_EXTENSIONS = ['.txt'] # --- Helper Functions --- def is_valid_file(filename): """ Checks if a filename is valid based on allowed extensions. Args: filename (str): The name of the file. Returns: bool: True if the file is valid, False otherwise. """ return any(filename.endswith(ext) for ext in ALLOWED_EXTENSIONS) def load_text_file(filename): """ Loads the content of a text file. Args: filename (str): The name of the file to load. Returns: str: The content of the file, or None if the file doesn't exist or is invalid. """ filepath = os.path.join(TEXT_DIRECTORY, filename) if not os.path.exists(filepath) or not is_valid_file(filename): return None try: with open(filepath, 'r', encoding='utf-8') as f: return f.read() except Exception as e: print(f"Error reading file: {e}") # Log the error return None # --- API Endpoints --- @app.route('/text/<filename>', methods=['GET']) def get_text(filename): """ API endpoint to retrieve the content of a text file. Args: filename (str): The name of the text file to retrieve. Returns: JSON: A JSON response containing the text content, or an error message. """ text_content = load_text_file(filename) if text_content is None: abort(404, description="File not found or invalid.") # Return a 404 error return jsonify({'filename': filename, 'content': text_content}) # --- Error Handling --- @app.errorhandler(404) def resource_not_found(e): """ Custom error handler for 404 errors. """ return jsonify(error=str(e)), 404 # --- Main Execution --- if __name__ == '__main__': app.run(debug=True) # Enable debug mode for development ``` **Explanation and Documentation (MCP Resources):** * **`TEXT_DIRECTORY`:** This variable *must* be updated to point to the actual directory where your text files from `Awesome-llms-txt` are located. This is crucial. * **`ALLOWED_EXTENSIONS`:** This list defines the file extensions that are considered valid. Adjust this if your files have different extensions. * **`is_valid_file(filename)`:** This function checks if a given filename is allowed based on its extension. This is a basic security measure to prevent arbitrary file access. * **`load_text_file(filename)`:** This function attempts to load the content of a text file. It handles file existence checks, extension validation, and potential file reading errors. The `encoding='utf-8'` is important for handling various character sets. Error handling is included to log potential issues. * **`@app.route('/text/<filename>', methods=['GET'])`:** This defines the API endpoint. The `<filename>` part is a variable that will be passed to the `get_text` function. The `methods=['GET']` specifies that this endpoint only accepts GET requests. * **`get_text(filename)`:** This function is the handler for the API endpoint. It calls `load_text_file` to retrieve the content of the specified file. If the file is not found or invalid, it returns a 404 error. Otherwise, it returns a JSON response containing the filename and the text content. * **`@app.errorhandler(404)`:** This defines a custom error handler for 404 errors. It returns a JSON response with an error message, which is generally better than the default HTML error page. * **`app.run(debug=True)`:** This starts the Flask development server. `debug=True` enables debug mode, which provides more detailed error messages and automatically reloads the server when you make changes to the code. **Do not use `debug=True` in a production environment.** **How to Run:** 1. **Install Flask:** `pip install Flask` 2. **Save the code:** Save the code above as a Python file (e.g., `api_server.py`). 3. **Update `TEXT_DIRECTORY`:** Modify the `TEXT_DIRECTORY` variable to point to the correct location of your text files. 4. **Run the server:** `python api_server.py` **Testing the API:** Once the server is running, you can test the API by opening a web browser or using a tool like `curl` and navigating to: `http://127.0.0.1:5000/text/your_file.txt` Replace `your_file.txt` with the actual name of a text file in your `TEXT_DIRECTORY`. **Example using `curl`:** ```bash curl http://127.0.0.1:5000/text/example.txt ``` **JSON Response (Success):** ```json { "filename": "example.txt", "content": "This is the content of example.txt." } ``` **JSON Response (Error - File Not Found):** ```json { "error": "404: File not found or invalid." } ``` **Important Considerations (Beyond the MCP):** * **Security:** This is a *very* basic example and is not secure for production use. You'll need to implement proper authentication, authorization, and input validation. * **Error Handling:** The error handling is minimal. You should add more robust error logging and reporting. * **Scalability:** Flask's built-in development server is not suitable for production. You'll need to use a production-ready WSGI server like Gunicorn or uWSGI. * **Configuration:** Hardcoding the `TEXT_DIRECTORY` is not ideal. You should use environment variables or a configuration file. * **Data Validation:** You might want to add more sophisticated data validation to ensure that the text files are in the expected format. * **Rate Limiting:** Implement rate limiting to prevent abuse. * **CORS:** If your frontend is hosted on a different domain, you'll need to configure CORS (Cross-Origin Resource Sharing). **MCP Principles Applied:** * **Minimal:** The code is as short and simple as possible while still demonstrating the core functionality. * **Complete:** The code includes all the necessary parts to run a basic API server. * **Verifiable:** You can copy and paste the code, install Flask, update the `TEXT_DIRECTORY`, and run the server to verify that it works. This MCP provides a starting point for building a more complex API server for your `Awesome-llms-txt` project. Remember to adapt it to your specific needs and to address the security and scalability considerations mentioned above. Let me know if you have any specific questions about any of these aspects.

dnomia-knowledge

Local knowledge engine for codebases with hybrid search, knowledge graph, and interaction tracking, enabling Claude Code to search and interact with project knowledge locally.

Anaplan MCP

An MCP server that connects AI assistants to Anaplan's Integration API v2, enabling users to browse workspaces, manage model data, and execute bulk operations like imports and exports. It provides 25 structured tools to navigate model hierarchies and perform transactional tasks through natural language.

google-mail-mcp

Provides a standardized interface for interacting with Google Mail tools and services through the Model Context Protocol, enabling email management via natural language.

fleet-mcp

A unified MCP server for managing hosting fleets, enabling natural language control over SSH, WordPress, Cloudflare, MySQL, GitHub, Docker, Coolify, and more.

AMapMCP

A FastAPI and fastmcp based Amap Navigation MCP tool that provides interactive map navigation with real-time route planning and WebSocket communication.

htb-app-mcp

Enables interaction with Hack The Box App services including machines, challenges, sherlocks, and more through the HTB API v4.

Second Opinion MCP

Enables Claude to consult over 17 AI platforms and 800,000+ models to provide alternative perspectives, code reviews, and diverse feedback. It features a unique personality system and supports multi-AI group discussions and debates directly within the chat interface.

Quran Cloud MCP Server

Connects LLMs to the Quran API (alquran.cloud) to retrieve accurate Quranic text on-demand, reducing hallucinations when working with sensitive religious content.

MCP Voice Notification

Provides voice notifications using Grok's text-to-speech API to alert users when Claude Code completes tasks, with support for both local and remote server configurations.

view-image-mcp

Enables Claude Code to display images inline within supported terminals like Ghostty and Kitty using the Kitty graphics protocol on macOS. It allows users to view various image formats including PNG, JPEG, GIF, and WebP directly in the terminal interface.

Ressl MCP Server - Advanced File Search

A sophisticated MCP server providing powerful file search capabilities including single file search, recursive directory search, and file information retrieval.

monarch-mcp-server

MCP Server for Monarch Money, utilizing an unofficial api.

FastMCP Webinar Demo Server

An MCP server with six tools including web search, URL fetching, math calculation, and note management. Designed for a live-coding demo integrating FastMCP with LangGraph ReAct agents.

MCP Calculator Server

A simple MCP server that provides an add_numbers tool for addition operations, with setup instructions for VSCode extensions like Roo Code or Cline.

LMS MCP Server

Automates interactions with the PAF-IAST University LMS to provide AI assistants with access to academic data like attendance, marks, and schedules. It features smart authentication with CAPTCHA solving and secure session management for seamless integration with tools like Claude and Cursor.

MCP Server Go

Uma implementação simples de servidor MCP escrita em Go.

Remote MCP Server on Cloudflare

Enables deploying a remote MCP server on Cloudflare Workers with OAuth login, allowing MCP clients like Claude Desktop to connect and use tools over SSE.

STRING MCP Server

Provides access to the STRING protein-protein interaction database for mapping identifiers, retrieving interaction networks, and performing functional enrichment analysis. It enables users to explore protein partners, pathways, and cross-species homology through natural language interactions.

zuul-mcp

MCP server for Zuul CI/CD with 25 tools for builds, pipelines, queue management (enqueue/dequeue/promote), infrastructure visibility, and autohold management. Supports stdio, HTTP, and SSE transports.

Junction41 MCP Server

MCP server for the Junction41 platform, providing 125 tools for agent lifecycle, jobs, workspace, payments, bounties, and more, enabling LLMs to interact with Junction41.

sendook-mcp

MCP server for Sendook - an AI email communication platform. Enables AI agents to send and receive emails, manage inboxes, threads, and webhooks programmatically.

mundane-mcp

Exposes the Mundane agent-to-human marketplace as MCP tools, enabling agents to post tasks, search workers, and make offers.

PhoneLCDParts MCP Server

A web scraping server that retrieves product information (name, price, URL, image) from phonelcdparts.com for any search query.