Browse the catalog

A self-contained daemon that watches a directory, transcribes anything that lands in it, and presents the results to any AI agent through a standard protocol — no cloud, no subscriptions, no vendor lock-in.

Enables AI agents to deploy multiplayer web games as playable URLs with rooms, live state sync, and leaderboards, all through a single tool call.

Provides a standardized MCP interface for querying Graylog logs, enabling AI agents to search, diagnose, and correlate runtime logs with code via configurable profiles.

A Figma MCP server that enables AI assistants to extract and process design elements from Figma files for React implementation. The server provides tools to retrieve processed Figma file content and component image URLs through the Figma API, transforming complex design data into structured formats ready for frontend development. It includes utilities for processing node positions, backgrounds, text styles, and auto-layout properties, making it valuable for developers who need to accurately translate Figma designs into React components without manual recreation.

An MCP server that gives AI agents live Google Hotels data (search, rooms, rates, cancellation) via internal RPC — no API key or scraping required.

Provides tools to build, package, and sign WebDriverAgent for iOS, enabling natural language automation of Appium WebDriverAgent preparation via MCP.

A minimalist MCP server that provides a single tool to retrieve a developer name, demonstrating the basic structure for Claude's Model Completion Protocol integration.

Enables AI agents to interact with the Hive swarm https://www.zhive.ai/ via REST API: register for an API key, save.

Provides a secure bridge for AI assistants to interact with the Google Sheets API via 31 tools for spreadsheet management, data manipulation, and table-level operations. It supports both Service Account and OAuth 2.0 authentication for tasks including batch updates, CSV imports, and conditional formatting.

This project provides sample MCP servers that can be used with Amazon Q CLI or other MCP-compatible AI assistants

MCP server for AI-assisted Minecraft modding: inspect decompiled source, resolve Mojang/Yarn/Intermediary mappings, diff versions, analyze Fabric/Forge/NeoForge mod JARs, and validate Mixin, Access Widener, and Access Transformer files.

MCP server for offensive-security tooling, enabling AI agents to run reconnaissance, CVE intelligence, JavaScript analysis, HTTP probing, and port scanning against authorized targets.

Enables multi-agent trend analysis for digital marketing, web design, and graphics design, routing requests through specialized agents to produce actionable recommendations and implementation plans.

Analyzes GitHub pull requests and creates detailed reports in Notion via MCP.

Enables natural-language shopping queries on a fashion inventory flat file, with tools for searching products and recommending matching items via OpenAI.

Browser and desktop UI for MCP servers — tools, resources, prompts, auth (Bearer, headers, OAuth), and optional trace logging.

Self-healing proxy for MCP servers that wraps tool calls with automatic retry, circuit breaker protection, and observability.

This RBDC MCP server by the rbdc team provides SQL database access through the RBDC (Rust Database Connectivity) framework, supporting SQLite, MySQL, PostgreSQL, and MSSQL databases with connection pooling and parameterized queries. The implementation offers three core tools: sql_query for SELECT operations, sql_exec for INSERT/UPDATE/DELETE operations, and db_status for connection pool monitoring, with automatic parameter conversion between JSON and RBDC value types. Built for developers who need reliable database access in AI workflows, it leverages RBDC's connection pooling and multi-database support to enable efficient SQL operations across different database systems with proper error handling and connection management.

This QuantConnect MCP server provides AI agents with quantitative finance research capabilities through the QuantConnect platform, offering 40+ tools across nine categories including QuantBook instance management, historical data retrieval, statistical analysis (PCA, cointegration, mean reversion), portfolio optimization with sparse algorithms, universe selection via ETF constituents, alternative data integration, project and file management, backtest execution and analysis, and authentication handling. Built with Python using the FastMCP framework and featuring comprehensive error handling, the implementation supports both local QuantConnect LEAN installations and cloud API access with proper authentication, making it valuable for algorithmic trading research, quantitative analysis workflows, portfolio construction, and building AI-powered financial assistants that need access to professional-grade financial data and analytics tools.

Monitor the real-time status of 200+ popular APIs and services. Check if services like GitHub, Stripe, AWS, and Slack are experiencing outages or degraded performance directly from your AI assistant.