Packages

Provides an MCP (Model Context Protocol) server wrapper for RapidAPI, enabling an agent to call RapidAPI-hosted endpoints via MCP tools (as opposed to direct REST calls).

workos-gdrive-mcp-server is an MCP (Model Context Protocol) server intended to expose Google Drive capabilities to an AI agent/workflow, typically via WorkOS-related integration patterns.

Provides a Zed Editor extension that connects Zed to Shortcut’s Model Context Protocol (MCP) server, allowing users to view/search and create/update Shortcut stories (and related objects) from within the editor’s AI assistant.

A general-purpose biomedical knowledge assistant that connects to multiple local MCP biomedical data sources (OpenTargets, Monarch, MyGene, MyChem, MyDisease), routes questions to the appropriate tools, and synthesizes answers with metadata such as confidence, citations, and limitations. Provides both a CLI and a Streamlit UI.

Provides a generic MCP (Model Context Protocol) server that uses CData JDBC drivers to expose external data sources as SQL-like tables/columns and lets MCP clients run queries (and, despite the repo name/readme emphasis, it claims CRUD tools are available via MCP tools). Communication with the MCP client is via stdio on the same machine.

Provides a Go-based MCP (Model Context Protocol) server that exposes GitHub-related tools (e.g., repository search/create, branch and file operations, issue operations, commits, and various searches) backed by the GitHub REST API.

Provides a local, read-only MCP server that exposes MYOB AccountRight data via CData JDBC driver models. The MCP server communicates over stdio to local AI clients (e.g., Claude Desktop) and offers tools to list tables/columns and run SELECT queries (SQL).

MCP server that integrates pgvector with Azure OpenAI for embedding generation and vector search workflows. It exposes vector/embedding-related capabilities to MCP-capable agents so they can index, query, and retrieve similar records using pgvector-backed storage.

MCP server that provides AI agents with access to Xiaohongshu (Little Red Book / RedNote) content, enabling keyword-based note search and note retrieval via URL through browser-based cookie authentication.

Provides a read-only Model Context Protocol (MCP) server that exposes SAS Data Sets via the CData JDBC Driver, letting an MCP-capable client (e.g., Claude Desktop) query live data using MCP tools (get tables, get columns, run SQL SELECT).

Provides an MCP server that lets an MCP-capable agent manage Uptime Kuma monitors (batch add, list, and delete) by calling MCP tools that in turn use the Uptime Kuma API. Includes a simple way to run an SSE endpoint via FastMCP/uvicorn.

Provides a Model Context Protocol (MCP) server (stdio or HTTP mode) with tools intended for security red-team testing. The README describes a tool, record_analytics, that simulates exfiltration/analytics behavior for security demonstrations.

Community Terraform provider for [F5 Distributed Cloud](https://www.f5.com/cloud).

<div align="center">

Itsyconnect is a local-first desktop app and self-hosted web dashboard that replaces parts of Apple App Store Connect. It manages app listing content across locales, handles TestFlight builds/testers and review/analytics workflows, and provides an optional MCP server so coding agents can manage store listing data from the terminal. Itsyconnect claims local-only operation with SQLite persistence and encrypted credential storage using AES-256-GCM with a master key stored in the macOS Keychain.

A Docker companion container that automates Let’s Encrypt certificate issuance/renewal for Nginx Proxy based setups (commonly with nginx-proxy/nginx-proxy-manager style), wiring certificate generation into the reverse-proxy workflow.

Provides an MCP server that dynamically exposes Liblib/ComfyUI workflows as MCP Tools, alongside a management UI and REST APIs for multi-tenant workflow and credential management.

MCP server package intended to provide an interface for browsing web content using Browserbase services. It exposes browser-browsing capabilities to an MCP-capable agent runtime (server-side).

Provides an MCP (Model Context Protocol) server that implements Anthropic's "think" tool, giving the model a structured thinking space, optional thought-history clearing, and basic metadata/statistics about thinking.

MEDUSA is an open-source (Python) AI-first security scanner/CLI that detects vulnerabilities and insecure patterns in traditional code as well as AI/ML and agent/LLM application artifacts (including prompt-injection style rules, RAG pipeline risks, MCP server configurations, and repo poisoning via editor/agent configuration files). It also supports scanning local directories and (optionally) cloning/scanning GitHub repos via a --git flag, producing reports in multiple formats (JSON/HTML/Markdown/SARIF).