Browse the catalog

Enables AI agents to interact with Apache Kafka through natural language, supporting operations like producing/consuming messages, managing topics, and querying brokers, partitions, and consumer group offsets.

A Model Context Protocol server that provides Git version control operations as structured tools for AI coding agents. It enables LLMs to programmatically manage repositories through actions like committing changes, rolling back code, and comparing diffs.

Provides desktop automation capabilities (e.g., click, browser snapshot) as MCP tools for DSH agents, enabling computer use via natural language.

Exposes a Bitvavo crypto exchange account as read-only tools for Claude, allowing portfolio queries, trade history, and market data without enabling trading.

An MCP server that enables users to fetch Python documentation using the Brave Search API through natural language queries.

Enables AI agents to perform dynamic and reflective problem-solving through a chain of thoughts, allowing them to break down complex problems, revise past thoughts, and explore logic branches before reaching a conclusion.

A Model Context Protocol server for macOS that enables AI assistants to play system sounds for audio feedback, offering informational, warning, and error sound options.

Resilient multi-CLI orchestration server for AI agents that routes tasks to Claude, Gemini, or Codex with automatic retry, circuit breaker, and fallback.

Real-time DeFi data for AI agents. Provides yields, TVL, prices, DEX volumes, fees, and contract data via 8 MCP endpoints, powered by DeFiLlama.

Remote MCP deployment scaffold for Skylight's MCP server, hosted on Cloudflare Workers and Containers, enabling HTTP access to the stdio-based Ruby MCP server.

An MCP server that provides comprehensive access to Adobe Spectrum 2 UI components with complete component coverage and lightning-fast performance via Cloudflare Workers.

An MCP server that integrates with fal.ai to provide AI agents with tools for image generation, text processing, audio synthesis, and model management via a unified interface.

Enables AI agents to check brand mentions across AI search surfaces like ChatGPT, Claude, Gemini, Perplexity, and Google AI Overviews using natural language queries.

Enables beginner-friendly Python and Pybricks development support through RAG-powered tools that search official documentation, suggest code snippets, and provide version-aware guidance for LEGO robotics programming.

Production-grade MCP server for Indian agriculture and utility workflows, enabling crop advisory, weather checks, mandi prices, and railway utilities through natural language.

Manage a Habitica account from Claude through a Claude Code skill, plugin, and MCP server.

Fetches and converts HTML documentation from reacticx.com into markdown format with 30-minute caching. Offers tools to list components by category, search by keywords, retrieve full component documentation with props and examples, and get installation commands. Covers 90+ animated components across categories like shaders, text effects, micro-interactions, and UI templates for React Native development.

Remote MCP server for 2ools—build, version, review, and export websites, web apps, and games from the AI chat you already use. This repository includes a credential-free stdio proxy and Dockerfile that forward introspection to the verified remote endpoint without mocking tools.

Read-only MCP server for PostgreSQL, written in Go. Schema introspection, safe SQL, query plans, database health checks, and index recommendations. A Go port of crystaldba/postgres-mcp.

Stimulus Docs MCP Server provides AI assistants with direct access to the Stimulus JavaScript framework documentation through a set of specialized tools. Built with TypeScript, it fetches documentation from the official Stimulus GitHub repository, caches content for performance, and exposes both handbook tutorials and technical reference materials as separate tools. The server implements fallback mechanisms to ensure reliability, first attempting to retrieve content from GitHub, then from local cache, and finally from bundled files. This implementation is particularly useful for developers seeking guidance on Stimulus controllers, actions, targets, and other framework features without leaving their AI assistant conversation.