Browse the catalog

MCP server that exposes Google Sheets as read-only resources, providing static and templated URI access to sheet data as CSV.

Locust MCP Server provides a bridge between AI assistants and the Locust load testing framework, enabling natural language control of performance testing operations. Developed by NaveenKumar Namachivayam, this implementation uses FastMCP to expose Locust's functionality through a standardized tool that configures and executes load tests with customizable parameters including number of users, spawn rate, and test duration. The server reads configuration from environment variables and manages the Locust subprocess, making it ideal for DevOps engineers and QA professionals who want to integrate performance testing into their AI-assisted workflows without manual command-line interaction.

Enables searching and retrieving course details, schedules, prerequisites, and instructor information from the CMU course catalog via the ScottyLabs API.

A slick, docker-ready Model Context Protocol (MCP) server powered by Spotipy—transforming Spotify playback, search, and playlist actions into handy MCP tools. Whether you want to play, pause, search, or curate your library through MCP clients (like Claude Desktop or Cursor), this server speaks Spotify while keeping your secrets safely in env vars.

DeFi execution on Base, Citrea, HyperEVM and Monad via Fibrous aggregation: swap quotes, swaps with optimal routing, native and ERC-20 transfers, cross-chain portfolio with USD valuations, and Aave V3 supply/borrow/repay/withdraw. Quotes, transaction status and Aave market data need no wallet, and transactional tools accept simulate=true for a preview that never broadcasts.

OKX v5 public MCP.

Interact with your HackMD notes and teams seamlessly. Manage your notes, view reading history, and…

Enables AI agents to efficiently manage and monitor background processes, with features like process startup, termination, log retrieval, and resource management.

Image and video understanding + generation for AI agents -- across Gemini, OpenAI, and Grok.

A Model Context Protocol (MCP) server implementation that integrates with Firecrawl for web scraping capabilities.

Genetic algorithms auto-evolve trading strategies from 484 factors. Crypto + A-shares + US stocks. Walk-forward validated. No API keys needed.

A Model Context Protocol server providing comprehensive tools to access real-time market data, trading information, user positions, and analytics for the Hyperliquid perpetual futures exchange.

This DuckDuckGo search implementation for the Model Context Protocol (MCP), developed by qwang07, enables AI models to perform web searches using the DuckDuckGo engine. Built with TypeScript and leveraging the duck-duck-scrape library, it provides a simple interface for querying DuckDuckGo and retrieving search results. The implementation stands out by offering easy integration with MCP-compatible AI systems and respecting DuckDuckGo's privacy-focused approach. It's particularly useful for AI assistants or applications needing up-to-date web information, enabling tasks like fact-checking, research, or providing current event updates without relying on potentially outdated training data.

MCP server for 402 Index: discover 15,000+ paid API endpoints across L402, x402, and MPP

This CouchDB MCP server, developed by Roberto Moreno, provides a bridge for AI assistants to interact with CouchDB databases. Built with TypeScript and leveraging the Model Context Protocol SDK, it offers tools for managing databases, documents, and Mango queries. The server automatically detects the CouchDB version to enable appropriate features, supporting basic operations across all versions and advanced Mango query capabilities for CouchDB 3.x+. It focuses on secure configuration management through environment variables and includes robust error handling. This implementation is particularly useful for applications requiring document database management, such as content management systems, data analytics platforms, or distributed web applications that need to leverage CouchDB's features through AI-driven interactions.

The PsMCP-MCP Server for Photoshop enables AI assistants to directly control Adobe Photoshop through a rich set of tools built with win32com. Developed by Chandrahas455, this Python implementation provides capabilities for manipulating layers, text, images, and effects in Photoshop documents through natural language commands. The server exposes over 30 tools for operations like opening/saving PSD files, creating and editing text layers, applying filters, managing layer properties, and exporting in various formats. It integrates with Gemini AI through a Gradio interface for a seamless user experience, making it particularly valuable for designers who want to automate Photoshop tasks or control their workflow through conversational AI without switching contexts.

Enables fetching and analyzing YouTube video comments and replies through the YouTube Data API. Supports sorting by relevance or time and returns structured JSON data for comment analysis, summarization, and translation tasks.

Linkly enables creation and management of branded short links with comprehensive analytics. Features include custom domains, UTM parameters, retargeting pixels, QR codes, geo and device-based targeting, link expiration, and real-time click tracking with detailed breakdowns by country, platform, browser, and referrer.

Renders PNG previews and STL geometry from OpenSCAD source code, enabling iterative agent-driven CAD workflows.

Provides Claude Desktop with access to WHOOP fitness data including recovery, sleep, strain, and workouts.