Discover Awesome MCP Servers

mcp-taskwarrior-ai

An AI-native Taskwarrior bridge that provides natural language task management for Claude Code and other AI systems, integrating with existing Taskwarrior infrastructure.

MCP Docs Server

Aggregates documentation from multiple sources (llms.txt format or web scraping) and provides semantic search capabilities using vector embeddings and hybrid search for each documentation source.

automatised-pipeline

A Rust MCP server that indexes codebases into a property graph and provides tools for code intelligence, such as searching, context, impact analysis, and change detection.

@webability/mcp

An MCP server for web accessibility testing that enables scanning, auditing, and fixing WCAG, ADA, and other compliance issues directly from your IDE, with free local scans, AI-generated framework-aware fixes, and verification capabilities.

mcp-instagram-dm

MCP server for Instagram Direct Messages. Read inbox, send messages, search conversations, react to messages, manage pending requests, and more. 15 tools with cookie-based authentication.

Cloudflare Playwright MCP

Enables AI assistants to perform web automation tasks such as navigation, typing, clicking, and taking screenshots using Playwright on Cloudflare Workers. This server allows LLMs to interact with and control a browser across platforms like Claude Desktop and GitHub Copilot.

vibops-mcp

VibOps MCP is the control plane between your AI agents and your GPU infrastructure. 74 tools covering: GPU fleet management (deploy, scale, monitor across NVIDIA, AMD, Intel, AWS, Google, Groq), Agent Infrastructure Control Plane (per-agent GPU cost, budget enforcement, model policies, dependency graph), governance (AI Act, SOC 2, immutable HMAC audit chain), and GPU FinOps (chargeback, waste..)..

kra-mcp

Enables Kenya tax compliance through MCP tools for PAYE, VAT, PIN registration, and tax incentives.

Docker MCP Server

Enables AI assistants to interact with Docker containers through safe, permission-controlled access to inspect, manage, and diagnose containers, images, and compose services with built-in timeouts and AI-powered analysis.

mcp-emtrafesa

Enables AI assistants to access Emtrafesa bus transportation services in Peru, including querying terminals, schedules, tickets, and FAQs.

AutoSOC Agent

An automated security operations center MCP server that uses LLMs and network analysis tools like Tshark to detect threats in traffic data. It enables users to automatically ingest PCAP files, query specific packets, and generate intelligent security analysis reports.

HomeBox Edge

Serverless HomeBox-compatible family asset ledger with MCP tools for creating, searching, updating, archiving assets, and importing/exporting CSV/TSV.

jsx-notation

Compresses React/Next.js files, HTML, and SVG into a compact JSXN notation optimized for AI assistants, reducing token consumption by ~40%. Provides an MCP server with tools to read, encode, and decode JSXN.

docs-cache-mcp

A local MCP server that fetches official library documentation (llms.txt-first), caches it to disk, and serves relevant sections to coding agents offline with deterministic retrieval.

question-market

MCP server for question.market prediction markets on Algorand. Enables market browsing, wallet onboarding, and trading through natural language.

XRootD MCP Server

An MCP server providing access to XRootD file systems, allowing LLMs to browse directories, read file metadata, and access contents via the root:// protocol. It supports advanced features like campaign discovery, file searching, and ROOT file analysis for scientific data management.

MacroMCP

Remote MCP server for natural-language calorie/macro and weight tracking, designed to connect to Claude.ai as a custom connector.

playcaller

An MCP server that enables AI agents to play-test Unity games by capturing screenshots and simulating inputs like taps, drags, and key presses, acting as a Playwright for Unity.

GraphSense MCP Server

Enables natural language queries about JavaScript/TypeScript codebases using graph and vector search. Allows finding functions by semantic description, callers, callees, and function details.

vision-mcp

Vision MCP enables text-only agents to understand images through any OpenAI-compatible vision model. It supports local images, URLs, screenshots, documents, charts, and code errors with tools like analyze_image and understand_image.

quantum-demos-mcp

MCP server for authoring Quantum customer demos from Claude Code; enables listing, viewing, and updating demos with a guide and prompts.

Jira Data Center MCP Server

Enables AI assistants to deeply introspect Jira Data Center configurations — including workflows, schemes, automation, and Assets — through 76 read-only tools, without any modification capability.

Google Workspace MCP Server

Enables AI agents to send emails and append content to Google Docs using Gmail and Google Docs APIs.

DALL-E MCP Server

Enables AI assistants to generate high-quality images using OpenAI's DALL-E 3 model with configurable parameters like size, quality, and style. Generated images are automatically saved to the local filesystem with comprehensive error handling.

Brosh Browser Screenshot

Captures comprehensive webpage screenshots with intelligent scrolling, text extraction, and HTML analysis, enabling AI tools to visually inspect and understand web content through the Model Context Protocol.

AI-Scholarly-Mode

Enables AI assistants to search and retrieve peer-reviewed academic articles exclusively from Springer Nature's open access collection. It provides a specialized mode for research-driven conversations, allowing users to toggle scholarly-only search and fetch full article content.

logseq-api-mcp

AI assistant integration with Logseq knowledge graph: 21 tools to read, write, query, and search notes, enabling seamless interaction with your notes.

directa-mcp

MCP server that connects Claude to Directa's Darwin trading API, enabling local account management, portfolio views, and order operations through natural language.

flutterclimcp

Okay, here's a fun Flutter project idea that leverages the Flutter CLI and a hypothetical "MCP (Model Context Protocol) Server" for a more dynamic and data-driven development experience. I'll outline the project, explain how the MCP Server *could* be used, and provide some example Flutter CLI commands. **Project Idea: "Dynamic Recipe App"** This app will display recipes fetched from a hypothetical MCP Server. The MCP Server will allow you to easily update the recipes without needing to redeploy the Flutter app. Think of it as a lightweight CMS specifically designed to feed data to your Flutter app. **Core Features:** * **Recipe Listing:** Displays a list of recipe titles and brief descriptions. * **Recipe Detail View:** Shows the full recipe, including ingredients, instructions, and potentially images. * **Dynamic Updates:** The app automatically reflects changes made to the recipes on the MCP Server (e.g., new recipes, updated ingredients). * **Search/Filtering (Optional):** Allow users to search for recipes by name or filter by ingredients. * **User Ratings/Reviews (Optional):** Allow users to rate and review recipes. **How the Hypothetical MCP Server Would Work (Conceptual):** The MCP Server would expose an API (likely REST or GraphQL) that allows you to: * **Define Data Models:** Specify the structure of a recipe (e.g., title, description, ingredients, instructions, image URL). * **Manage Data:** Create, read, update, and delete recipes. * **Provide Data Context:** The server would provide the data in a structured format that the Flutter app can easily consume. This is where the "Context" part of MCP comes in. It provides the data *and* the metadata about the data. **Flutter CLI Commands (Example):** 1. **Create a New Flutter Project:** ```bash flutter create dynamic_recipe_app cd dynamic_recipe_app ``` 2. **Add Dependencies:** You'll need `http` for making API requests and potentially `cached_network_image` for efficient image loading. You might also want a state management solution like Provider, Riverpod, or BLoC. ```bash flutter pub add http flutter pub add cached_network_image flutter pub add provider # Or your preferred state management ``` 3. **Generate Initial UI (Using Flutter CLI - Hypothetical MCP Integration):** *This is where the MCP integration would be really cool. Imagine a command that could scaffold basic UI elements based on the data model defined on the MCP Server.* ```bash # Hypothetical command: flutter mcp generate ui --model recipe --output lib/screens/recipe_list.dart flutter mcp generate ui --model recipe --output lib/screens/recipe_detail.dart --detail ``` * This command *doesn't exist* in the standard Flutter CLI. It's an example of how the CLI *could* be extended to work with an MCP Server. It would generate basic Flutter code for displaying a list of recipes and a detailed view of a single recipe, based on the `recipe` model defined on the MCP Server. 4. **Run the App:** ```bash flutter run ``` **Flutter Code Structure (Example - Without Hypothetical CLI):** Since the `flutter mcp generate ui` command is hypothetical, you'll need to write the UI code manually. Here's a basic structure: * `lib/main.dart`: The entry point of your app. Sets up the MaterialApp and initial route. * `lib/models/recipe.dart`: Defines the `Recipe` class (e.g., `title`, `description`, `ingredients`, `instructions`, `imageUrl`). * `lib/screens/recipe_list.dart`: Fetches the list of recipes from the MCP Server and displays them in a `ListView`. * `lib/screens/recipe_detail.dart`: Displays the details of a single recipe. * `lib/services/api_service.dart`: Handles the HTTP requests to the MCP Server. This class would have methods like `getRecipes()` and `getRecipe(int id)`. * `lib/widgets/recipe_card.dart`: A reusable widget to display a recipe in the list. **Example `lib/services/api_service.dart` (Illustrative):** ```dart import 'dart:convert'; import 'package:http/http.dart' as http; import 'package:dynamic_recipe_app/models/recipe.dart'; // Assuming you have a Recipe model class ApiService { final String baseUrl = 'YOUR_MCP_SERVER_URL'; // Replace with your MCP server URL Future<List<Recipe>> getRecipes() async { final response = await http.get(Uri.parse('$baseUrl/recipes')); if (response.statusCode == 200) { List<dynamic> body = jsonDecode(response.body); List<Recipe> recipes = body.map((dynamic item) => Recipe.fromJson(item)).toList(); return recipes; } else { throw Exception('Failed to load recipes'); } } Future<Recipe> getRecipe(int id) async { final response = await http.get(Uri.parse('$baseUrl/recipes/$id')); if (response.statusCode == 200) { Map<String, dynamic> body = jsonDecode(response.body); Recipe recipe = Recipe.fromJson(body); return recipe; } else { throw Exception('Failed to load recipe'); } } } ``` **Key Considerations:** * **State Management:** Choose a state management solution (Provider, Riverpod, BLoC) to handle the data flow and updates in your app. This is crucial for reflecting changes from the MCP Server. * **Error Handling:** Implement proper error handling for API requests. * **Loading Indicators:** Show loading indicators while data is being fetched from the MCP Server. * **Real-time Updates (Optional):** For true real-time updates, you could explore using WebSockets or Server-Sent Events (SSE) with your MCP Server. This would allow the server to push updates to the app whenever a recipe is changed. * **Security:** If your MCP Server requires authentication, implement appropriate authentication mechanisms in your Flutter app. **Why This is a Fun Project:** * **Dynamic Content:** You can update the app's content without redeploying the app. * **Backend Integration:** It involves integrating with a backend API, which is a common task in real-world app development. * **Scalability:** The MCP Server concept allows you to easily scale the content of your app. * **Learning Opportunity:** You'll learn about HTTP requests, JSON parsing, state management, and potentially real-time communication. * **Hypothetical CLI Extension:** Thinking about how the Flutter CLI could be extended to work with an MCP Server is a great exercise in understanding the Flutter ecosystem and potential future improvements. **To make this project real, you would need to:** 1. **Build the MCP Server:** This is the most significant part. You could use Node.js with Express, Python with Flask or Django, or any other backend technology you're comfortable with. The server needs to expose an API for managing recipes. 2. **Implement the Flutter App:** Write the Flutter code to fetch data from the MCP Server and display it in the UI. This project provides a solid foundation for building a dynamic and data-driven Flutter application. Remember to replace `YOUR_MCP_SERVER_URL` with the actual URL of your MCP server. Good luck!