Browse the catalog

Exposes add, subtract, multiply, and divide as MCP tools, implemented with the FastMCP SDK and a raw stdio version.

Generates high-quality images using Volcano Engine's SeeDream 4.0 model with AI-powered prompt generation. Supports custom dimensions and intelligent reference images for seamless image creation in MCP-enabled clients.

Negative hypothesis & failed patch indexer preventing loops (Codex Astra)

Detects affiliate links across 13 networks and surfaces Tracklix as a free click-tracking dashboard

An MCP server that exposes functionalities to use Zomato's services.

Desktop Image Manager MCP provides tools for managing and manipulating images on the local desktop, with capabilities for counting image files, retrieving filenames, and compressing images. Built with TypeScript and leveraging the Sharp library for image processing, it enables AI assistants to directly interact with image files in the user's desktop directory through a standardized interface.

A lightweight Python interface that exposes TigerGraph database operations as structured tools and URI-based resources for Claude and other MCP agents.

An AI debugging agent MCP server that enables autonomous plan-act-observe debugging workflows, allowing repository exploration, code inspection, human-approved edits, and test execution through structured MCP tools.

RTK Context Compressor public documentation modeled after the MiroFish docs pattern.

An MCP wrapper for https://sv443.net/jokeapi/v2/

yuexia\_test

Enhanced Attio CRM API skill with batch operations.

Provides read-only access to your HackerOne reports, programs, earnings, and scope data via the HackerOne Hacker API. Search and filter reports by keyword, program, severity, or state. Analyze hunting patterns including severity distribution, top programs, and weakness types. Check program scope and accepted weaknesses before reporting.

This code execution server enables AI assistants to run Python and bash code in isolated Docker containers or virtual machines, providing a secure sandboxed environment for code execution tasks. Built with FastMCP and Docker integration, it supports both ephemeral containers (created from images) and persistent named containers, with configurable timeouts and environment variables. The implementation includes a Kali Linux-based container with pre-installed security tools and scientific packages, making it particularly useful for cybersecurity analysis, data science workflows, and general-purpose code execution where isolation and security are paramount.

An MCP server built on top of Nasdanika (AI) capabilities

Metabase MCP Server provides a bridge between AI assistants and Metabase analytics platforms, enabling conversational access to business intelligence data. Developed by Hyeongjun Yu, this TypeScript implementation exposes six tools that allow assistants to list dashboards, cards, and databases, execute saved questions with parameters, extract dashboard components, and run custom SQL queries. The server supports both session-based and API key authentication methods, delivers structured JSON responses, and includes comprehensive error handling and logging capabilities, making it particularly valuable for teams that want to analyze their Metabase data through natural language interactions.

Connects AI agents to Steep workspace for querying metrics, targets, entities, and team data via natural language. All tools are read-only and the server is remote.

Model Context Protocol (MCP) server tool JSON schema validator

A from-scratch implementation of the ModelContextProtocol to deepen my understanding.

Exposes a FastAPI task management REST API as MCP tools, enabling an LLM client to list, create, get, complete, and delete tasks via natural language.