Browse the catalog

Renders Markdown into a browser-based, click-to-comment thread; comments are returned to Claude as tool results.

This MCP server provides AI assistants with complete YouTube API access and management capabilities, built by eat-pray-ai using Go with Cobra CLI framework and featuring both command-line interface and MCP server modes for programmatic YouTube operations. The implementation offers full CRUD operations across all major YouTube resources including videos, playlists, channels, comments, captions, subscriptions, and analytics data, with support for video uploads, thumbnail management, live streaming controls, and content moderation workflows through the official Google YouTube Data API v3. Built with Bazel build system, Docker containerization, OAuth2 authentication with token caching, flexible output formats (JSON, YAML, table), and JSONPath filtering capabilities, it serves content creators needing conversational access to YouTube channel management, social media managers requiring AI-driven video publishing and analytics workflows, and development teams where natural language interfaces enhance YouTube integration without direct API knowledge.

An MCP server that uses Playwright to scrape Israeli weather forecasts from weather2day.co.il by automating a real browser, enabling an LLM to answer questions about current conditions and hourly forecasts for Israeli cities.

Provides compact, assistant-friendly tools for NASA's public APIs, including APOD, space weather, Earth events, and media library, without flooding the context window.

This MCP server requires user authentication via Auth0 and then enables calling protected APIs (e.g., a Todos API) on behalf of the user.

Enables remote access to Baserow workspaces over Streamable HTTP, allowing discovery of accessible tables and creation of rows using user-facing field names.

Control Classic Mac OS (System 7-9) from AI agents via shared folder protocol.

A living companion in your MacBook notch: music, notes, calendar, Jira, calls and AI. Free & open source (beta)

Enables basic arithmetic operations (add, subtract, multiply, divide, modulo) via natural language, with a FastMCP-based server and client for exploring MCP tool calling.

A minimal MCP server that lets an MCP client run shell commands on remote hosts over SSH, with host, key, user, and port chosen per call.

Provides isolated bash execution in Docker containers with multiple security layers: network isolation, Linux capability dropping, filesystem restrictions, and a command blocklist. Designed for AI agent workflows that need to run shell commands safely without risking host system compromise. Each execution runs in a fresh container with configurable resource limits.

An API server that enables interaction with IBM Maximo resources like Assets and Work Orders, providing tool functions to retrieve and list asset information.

The website o KineticMCP, an MCP server to automate salesforce with AI

MCP server for the On the Cheap network — local guides to free and cheap things to do across 14 US cities. Provides daily event listings with times, prices and venues, plus a searchable archive of deals and guides.

This MCP server provides weather forecasts from LandiWetter, a Swiss weather service. Developed by Nando Bosshart, it exposes tools for searching locations and retrieving detailed weather forecasts including temperature ranges, precipitation probability, wind conditions, and sunshine duration. The implementation includes both a core MCP server component that communicates via stdio and a test HTTP wrapper for easier integration testing. It's particularly useful for applications needing reliable Swiss-specific weather data through a standardized MCP interface.

Enables AI assistants to search and analyze logs in Graylog using three powerful tools: generic log search with Lucene queries, smart UUID/trace ID lookup across multiple fields, and stream-specific message retrieval with automatic field normalization.

A read-only MCP server for querying U.S. K-12 academic standards via the Common Standards Project API.

MCP server that retrieves children's school information from Wilma and sends automatic summaries via WhatsApp.

This MCP server implementation, developed by Scott Spence, provides embedding search capabilities for transcripts. It utilizes a SQLite database to store and query embeddings, allowing for efficient semantic search across large volumes of text data. The implementation is designed for use cases requiring quick retrieval of relevant transcript segments based on semantic similarity, such as in podcast analysis, speech-to-text applications, or content recommendation systems.

BestTime MCP — foot-traffic / venue busyness forecasts (besttime.app)