Browse the catalog

An MCP server that enables AI agents to read, search, and write to your Obsidian vault.

This repository provides an empty Playwright test framework that was designed to test AI and Playwright MCP (Model Context Protocol) in course

Kogna MCP Server provides access to a multi-agent AI avatar room engine through a bridge architecture that forwards MCP requests to a hosted backend service at kogna.up.railway.app. Built by Subbu Bhamidipati, it offers tools for starting conversations with specialized AI avatars, switching between different rooms and avatars, sending messages, retrieving conversation history, and managing session state across multiple platforms (Slack, WhatsApp, Cursor). The implementation includes both a command-line MCP bridge and HTTP proxy components with proper session management using platform-specific user IDs and channel identifiers, making it useful for building conversational AI applications, multi-agent chat systems, and platform-agnostic AI assistant integrations.

Directus MCP Server provides a bridge between AI assistants and Directus headless CMS through a comprehensive set of API tools. This TypeScript implementation enables content management operations including retrieving, creating, updating, and deleting items from collections, as well as accessing system information, user management, file operations, and schema exploration. The server supports authentication via access tokens or email/password login, with configuration possible through environment variables or command-line arguments, making it particularly useful for AI-assisted content management workflows and headless CMS integration.

Provides real-time cryptocurrency data from CoinGecko, including prices, market data, historical data, and coin search.

Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys, no Docker, just a linked device.

Enables read-only access to SwanLab workspaces, projects, runs, and metrics through the Model Context Protocol.

Enables AI assistants to extract design systems, brand guidelines, copy, and sitemap structure from any live website via the Pastebase API.

An MCP server that reads a clinical note and returns ranked ICD-10-CM diagnosis code candidates with clinical reasoning, validated against official CMS coding constraints.

Exposes USC's public course catalog API to AI agents, enabling natural-language queries about courses, GE requirements, schedules, and fees with optional filters for days, times, and open sections.

Enables MCP-compatible AI hosts to read, search, link, and write notes in a local Obsidian vault with sandboxed file access.

Detects GTM hiring activity from company career pages via Greenhouse, Lever, Ashby. Clay-ready.

A lightweight, structured, token-efficient local-first MCP memory server

This project is a production-ready MCP server that bridges any LLM — Claude, GPT, Gemini, or open-source models with custom tools, prompt-driven skills, and remote server networks through a single, unified protocol layer.

A fork of the JetBrains MCP Server that adds WebSocket monitoring capabilities, allowing real-time observation of all MCP tool calls between clients (like Claude Desktop) and JetBrains IDEs. Created by Daniel Ortega, this proxy sidecar maintains full compatibility with the original implementation while broadcasting detailed information about each endpoint call and its arguments through WebSocket on port 27042. It's particularly useful for developers who need visibility into MCP interactions for debugging, monitoring, or extending IDE integration functionality.

Locale detect, translations, plurals for AI agents

Bridges Claude Cowork/Desktop to a local Hermes Agent, exposing hermes_delegate, hermes_check_run, and hermes_health tools for task delegation, status polling, and health checks.

An MCP server that lets any MCP-capable agent spawn and drive Claude Code sessions — effectively turning Claude Code into an orchestratable sub-agent fleet.

PII detection agent

This Replicate MCP server, developed by Tzafrir Rehan, provides a standardized interface for AI assistants to interact with various AI models hosted on Replicate. Built using Python and FastMCP, it currently focuses on image generation capabilities, offering model schema inspection, customizable parameter inputs, and output resizing. The server abstracts the complexities of the Replicate API, handling authentication, model execution, and result processing. It's designed for AI developers and researchers who need flexible access to state-of-the-art AI models, enabling use cases like dynamic image creation, model exploration, and integration of advanced AI capabilities into broader applications. The implementation's roadmap includes expanding support for text and video generation models, as well as adding features like version management and caching.