Browse the catalog

This Apple Health MCP server by neiltron provides programmatic access to Apple Health data stored in the Health app's SQLite database, enabling AI assistants to query and analyze personal health metrics including steps, heart rate, sleep patterns, workouts, and other HealthKit data points. The implementation reads directly from the Health app's local database files, allowing users to explore their health trends, generate insights about their fitness progress, and answer questions about their wellness data through natural language interactions. Built for personal health analytics workflows, it's particularly useful for users who want to understand their health patterns, track fitness goals, and get personalized health insights without manually navigating through the Health app's interface.

MCP server that provides read and write access to Trello boards, enabling AI assistants to list, search, create, update, move, comment, label, and archive cards via natural language.

Enables AI applications to interact with Tableau for querying data, exploring content, and retrieving views through natural language.

College Scorecard MCP — US Department of Education College Scorecard API

Search and browse the Agent Almanac catalog of MCP servers from within any MCP-compatible agent. Discover available servers, find implementations for specific tasks, and explore the MCP ecosystem without leaving your agent environment.

Official MCP server for HumanTone, enabling AI text humanization and AI likelihood detection directly from MCP clients like Claude Desktop and Cursor.

A Model Context Protocol (MCP) server that provides a simple sleep/wait tool, useful for adding delays between operations such as waiting between API calls or testing eventually consistent systems.

MCP server for sending Gotify push notifications to your devices.

A hands-on demonstration project that teaches the Model Context Protocol (MCP) through Python code, allowing users to understand how AI models interact with their context through a provider-agent architecture.

MCP server for monitoring, diagnosing, and auto-correcting observability issues across platform services, integrating with Sentry and PostgreSQL for error tracking and billing pipeline health.

Enables AI agents to perform e-commerce operations through a standardized interface implementing the x402 and Agentic Commerce Protocol (ACP). Supports merchant sessions, product search, and payment orchestration with production-ready security features.

An MCP server implementation for interacting with self-hosted Confluence Data Center or Server instances via search, content retrieval, and optional write operations. It features space auto-discovery, audit logging, and granular access control for secure enterprise collaboration.

Ramp MCP provides a bridge to the Ramp API, allowing AI assistants to access and interact with Ramp credit card and spend management data. Built by Khoi Le, this TypeScript implementation requires a Ramp API key and client ID for authentication, and can be installed via Smithery or run locally. The server enables users to query their credit card transactions and other Ramp data directly within MCP clients like Cursor or Claude Desktop, making it useful for financial tracking and spend analysis workflows.

Exposes Arrakis VM sandbox functionality to LLMs, enabling sandbox management and command execution.

Manage Apple Reminders with natural language from any MCP client; supports adding, showing, editing, completing, deleting reminders and managing reminder lists.

Enables AI assistants to manage a real estate pipeline by adding, listing, getting, and updating leads through KPI DealFlow.

MCP server for Google Ads — 22 tools for spend diagnosis, impression share, and asset performance.

A Model Context Protocol server for Hetzner Cloud API, developed by Dennis Kruyt, that enables language models to manage cloud infrastructure resources through structured functions. The implementation provides tools for creating and managing servers, volumes, firewalls, and SSH keys on the Hetzner Cloud platform, with comprehensive error handling and detailed response formatting. It supports both stdio and SSE transport modes, making it compatible with Claude Code and other MCP clients, and is particularly useful for AI-assisted cloud infrastructure management, automated provisioning, and infrastructure-as-code scenarios.

An immersive Role-Playing Game server built on the Model Context Protocol for interactive storytelling with AI assistants like Claude.

Enables MCP-compatible clients to search, read, and manage Confluence Cloud pages, including publishing and updating documentation from Markdown, with support for folders and secure API token storage.