Browse the catalog

A central repo for MCP Server research, development, & testing

viewport-control is a TypeScript-based MCP server that enables advanced browser automation for viewport management, screenshot capture, and content extraction. It is designed for integration with MCP clients (such as Claude Desktop) and provides a robust API for launching, resizing, and closing Chromium-based browser

Iceberg MCP is a Rust-based server implementation that provides AI assistants with access to Apache Iceberg catalogs. Developed by Morris Tai, it currently supports REST catalogs with plans for AWS Glue, S3 Table, and Hive metastore integration. The server exposes five key tools for data exploration: listing namespaces and tables, retrieving table schemas, accessing table properties (including size and record count), and examining table partitions. Built with async support and comprehensive logging, it's particularly valuable for data engineers and analysts who need to explore and understand Iceberg data lakes through AI assistants without writing complex catalog interaction code.

This is a template for creating Model Context Protocol (MCP) Servers in C# with a "close to clean" architecture.

MCP server for Discord bot API that exposes five tools to search, inspect, and call stable Discord HTTP endpoints using bot-token authentication, with automatic schema refresh and strict safety filtering.

Enter Plaza One, a 3D voxel social world.

This Ruby-based AI pair programming MCP server by K4sku provides five specialized tools for collaborative software development: general pair programming assistance, code review, brainstorming, performance analysis, and security review. Built using the FastMCP framework and RubyLLM library, it integrates with multiple AI models through OpenRouter including Gemini, O3, Grok, DeepSeek, and Claude Opus, with automatic gem installation via inline bundler for easy deployment. The implementation is particularly valuable for developers who want AI-powered code analysis and collaboration directly within their development workflow, offering configurable model selection and temperature settings for different types of programming tasks from creative brainstorming to rigorous security audits.

A demonstration MCP server built in TypeScript that shows how to implement stdio-based communication for integration with MCP clients. Serves as a template for building custom MCP servers with strong typing and maintainability.

An MCP server that provides image search capabilities via the Brave Image Search API, allowing AI assistants to search images with various filters and perform batch queries.

This MCP server implementation provides a bridge to OpenAPI-specified services, enabling AI assistants to interact with any API that follows the OpenAPI standard. Developed by Ross Masters, it dynamically generates MCP tools from an OpenAPI specification URL, allowing for seamless integration with a wide range of RESTful APIs. Built with Python and leveraging libraries like FastAPI and openapi3-parser, the server focuses on flexibility and ease of use. It supports OpenAPI 3.0 and 3.1 specifications in both JSON and YAML formats. The implementation is particularly useful for scenarios requiring interaction with multiple APIs, rapid prototyping, or integration with existing OpenAPI-documented services.

Self-hosted MCP server for secure AI access to SAP Adaptive Server Enterprise.

An MCP server that provides long-term memory and semantic search using Qdrant and OpenAI embeddings, with tools for storing, searching, and managing knowledge.

A production-ready MCP server providing file, system, math, and text utilities through a simple CLI client.

MCP server for sovereign AES-256-GCM backup encryption and decryption. Enables encrypting, decrypting, verifying, and scoring passphrases with zero network calls.

Provides real-time air quality data (US AQI, PM2.5, PM10, ozone, NO2, SO2, CO) for any city via natural language, using free Open-Meteo data and a single tool.

A demonstration MCP server built with TypeScript and Bun that implements a classic Magic 8-Ball oracle. It enables users to ask yes/no questions, use prompt templates, and access the full list of classic responses.

MCP server deployed on Azure Functions that provides a LearnAgent tool to search and retrieve Microsoft Learn documentation.

A collection of high-performance Claude skills and MCP servers. Featured: API Design Reviewer for REST, GraphQL, and gRPC audits.

Agentic cart bundle affinity recommender & AOV optimization (Rebuy style)

Build client-ready web scrapers with clean data output.