Browse the catalog

The kube-mcp server provides AI assistants with direct access to Kubernetes cluster operations through a set of specialized tools built with Python using the FastMCP framework. It enables capabilities like listing, creating, and managing pods, deployments, and services, as well as retrieving logs and cleaning up resources. The implementation includes predefined container templates for common images (Ubuntu, Nginx, Busybox, Alpine) with appropriate resource limits and health checks. It's particularly valuable for DevOps workflows requiring Kubernetes management within AI assistant conversations, allowing users to monitor cluster state, deploy test containers, and troubleshoot issues without switching to separate command-line tools.

A starter template for building MCP servers that enable AI assistants to interact with custom tools and data.

Zero Trust Access AI Agent - MCP Server

Grade any bet against thousands of play-by-play game simulations: win probability, odds, edge.

Exposes tic-tac-toe game tools (new_game, get_state, make_move) for Claude to play against a human via chat.

Extract UI structure from screenshots for text-only LLMs with a pure Go, offline, MCP-native binary.

Identifies knowledge gaps in markdown vaults, ranks them by priority, generates research questions, and offers long-tail sampling to break confirmation bias.

Provides Claude agents with CRM contact lookup, action logging, and prompt cost auditing tools. Includes a Streamlit UI to demo the same tools without an MCP client.

Query real-time and historical financial data across equities and crypto—prices, market moves, metrics, and trends.

Enables billing automation via natural language by creating a Composio MCP server that connects to Gmail, Google Sheets, Xero, and more for invoice generation, expense tracking, and payment processing.

This MCP server verifies that an agent’s claimed tool output matches the actual response returned by a tool to prevent invented or distorted results. It flags mismatches, omissions, and invented fields to ensure downstream logic only processes verified tool data.

Integrates with Claude to enable intelligent querying of documentation data, transforming crawled technical documentation into an actionable resource that LLMs can directly interact with.

A Node.js server that provides advanced video and image processing capabilities through the Model Context Protocol, enabling operations like conversion, compression, editing, and effects application.

Track average brand and product visibility metrics across LLM searches

Delivers macroeconomic intelligence powered by FRED (Federal Reserve Economic Data) and ECB sources. Provides tools for tracking Fed rates, inflation metrics, yield curve analysis, labor market indicators, GDP growth data, housing statistics, and a comprehensive macro dashboard. Part of the ToolOracle suite of MCP-native intelligence tools.

Remote MCP server for searching and aggregating Japan's administrative procedures survey data, powered by Cloudflare Workers and D1.

An MCP server built with FastMCP that currently provides a simple mathematical addition tool. It includes environment configurations for GitHub repository integration, suggesting future functionality for managing or uploading content.

Search, book, and manage scientific research equipment across 500+ STEM core facilities.

Enables search, reading, and posting to Bluesky from any MCP client; features 11 tools (5 read, 6 write) with gated writes requiring explicit confirmation to prevent accidental publishing.

Enables LLMs to read, write, and manage Apple Notes directly via markdown, including listing, fetching, creating, and appending notes.