Browse the catalog

Provides a standardized interface for interacting with Microsoft Teams tools and services through the Model Context Protocol.

This MCP server implementation provides a simple interface for extracting web page content using the Tavily API. It utilizes the FastMCP framework and exposes a single tool, 'extract_url', which takes a URL as input and returns the extracted content. The server requires a Tavily API key to be set as an environment variable and is designed for easy integration into projects that need web scraping capabilities.

Model Context Protocol server for Archive of Our Own: search fanfiction and have an AI read and rank fics for you.

A set of nine tools for AI agents with micropayments in USDC on Base, including on-chain intelligence, web search, document parsing, and more.

Enables searching and downloading photos from Unsplash via the Unsplash API, with support for pagination, orientation filtering, and multiple resolutions.

A lightweight, configuration-driven MCP server that ingests a CSV of acronyms and initialisms to expose a lookup tool for their full meanings and descriptions.

Enables interaction with Ethereum-compatible smart contracts through their ABI, allowing both read operations (querying state) and write operations (executing transactions) dynamically based on the contract's interface.

SEC ADV / IAPD MCP — SEC Investment Adviser Public Disclosure (Form ADV) lookup

A basic starter project for building Model Context Protocol (MCP) servers that enables standardized interactions between AI systems and various data sources through secure, controlled tool implementations.

A community-curated list of MCP (Model Context Protocol) servers. PRs welcome! Browse AI tools, integrations, and developer resources.

The MCP-CEP server provides a simple interface for querying Brazilian postal codes (CEPs) via the ViaCEP API. Developed by Wendell Barreto, this implementation runs as a stdio-based server that allows AI assistants to retrieve address information directly from Brazil's postal code database. The server is built using Python with the httpx library for API requests and the MCP framework for standardized communication. It's particularly useful for applications that need to validate or expand Brazilian addresses based on postal codes without requiring users to leave their conversation context.

This MCP server, developed to access BART (Bay Area Rapid Transit) departures data, provides real-time information on train schedules and station updates. Built with TypeScript and leveraging the Model Context Protocol SDK, it offers a simple interface for querying BART's API and retrieving structured departure information. The implementation stands out by focusing specifically on BART data, making it ideal for applications or AI assistants needing up-to-date public transit information for the San Francisco Bay Area. It's particularly useful for commuters, travel planners, or local businesses looking to integrate real-time BART data into their services or decision-making processes.

Apricot MCP public description

ArcGIS Pro MCP server by nicogis that enables AI assistants to interact with ArcGIS Pro desktop GIS software through a bridge architecture consisting of a .NET add-in running inside ArcGIS Pro and a separate MCP server process that communicates via inter-process communication. The implementation uses named pipes or similar IPC mechanisms to allow the MCP server to execute GIS operations, access map data, and control ArcGIS Pro functionality from external applications while maintaining the full desktop GIS environment. Built with C# for the ArcGIS Pro add-in component and .NET for the MCP server, this architecture enables AI assistants to perform spatial analysis, map creation, and GIS workflows without requiring direct API access, making it valuable for geospatial professionals who need conversational access to desktop GIS capabilities and automated spatial data processing tasks.

MCP server for Kubernetes FinOps that finds over-provisioned workloads, proposes right-sizing, and enforces safety guardrails with dry-run by default and audit logging.

Connect AI agents to your test results, insights, and targets. Query test runs, failures, flaky tests, and regressions across frameworks including Playwright, Jest, Pytest, Cypress and more.

This Azure Table Storage MCP server, developed by Christia Pedersen, provides AI assistants with a standardized interface to interact with Azure Table Storage. Built using TypeScript and leveraging the @azure/data-tables library, it offers capabilities for storing, retrieving, and querying structured data in the cloud. The server abstracts the complexities of Azure Table Storage operations, handling authentication, data serialization, and query optimization. It's particularly valuable for developers and AI systems working with large-scale, semi-structured data, enabling use cases such as log data storage, user profile management, and IoT telemetry processing within the Azure ecosystem.

Enables natural language analysis of network packet captures, including protocol detection, flow analysis, and security threat identification, integrated with AI assistants.

A demonstration MCP server for local development and testing with Claude Desktop on WSL. Provides basic utility tools including greeting messages, echo functionality, and server information retrieval.

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independently (via SSE or STDIO), offering modularity and cloud-deployable execut