Packages

mcp-applemusic is an experimental MCP server for macOS that controls Apple Music using AppleScript. It exposes MCP tools to play/pause/skip tracks, search the library, play a specific song, manage playlists, and return basic library statistics.

MCP Bundles (MCPB) is a TypeScript/Node.js toolchain and bundle format for packaging a local MCP server into a single .mcpb (zip) archive with a manifest.json describing server entrypoints and capabilities. It includes a CLI (mcpb init/pack) and reference code used by Claude for macOS/Windows to load, verify, and provide single-click installation with related end-user features like updates and configuration.

An MCP server that automates SAP GUI interactions for LLM agents by launching SAP transactions and controlling the GUI via simulated mouse/keyboard actions (including screenshot-based feedback).

MCP server that provides Model Context Protocol integration with Shopify, enabling programmatic access to Shopify APIs and data through the MCP framework

MCP server package - orange-mcp-server

MCP server package - orange-mcp-server-box

MCP server providing code assistance and development tooling through the Model Context Protocol

MCP server that collects and aggregates data from various sources

MCP server package providing headless Gmail API integration - enables programmatic access to Gmail functionality through the Model Context Protocol without UI

Provides a Model Context Protocol (MCP) server that exposes OSDU platform capabilities (health/entitlements, partition management, legal tags, schema management, search, and storage CRUD with versioning/batching) through conversational tool calls.

Provides a local, stdio-based MCP server wrapper around the CData JDBC Driver for SAP Ariba Procurement, exposing available tables/columns and a SQL SELECT query tool to an MCP-capable client (e.g., Claude Desktop). The server is described as read-only in this repo.

Provides an MCP (Model Context Protocol) server that lets an agent retrieve SwitchBot device lists and statuses and execute commands on SwitchBot devices using SwitchBotAPI credentials.

Provides a Model Context Protocol (MCP) server for interacting with Talos Linux clusters using talosctl’s underlying gRPC/mTLS API. Exposes Talos cluster/node lifecycle operations, configuration/pache workflows, resource inspection, and supporting utilities like file browsing/reading, logs/dmesg, and etcd management.

Provides an MCP server that exposes Utsunomiya City open data via natural-language queries and MCP tools (list datasets, get dataset schemas, query dataset contents, and analyze datasets with caching).

Provides an MCP server integration for Zed that exposes a `convert_to_markdown(uri)` tool to convert documents (PDF/DOCX/XLSX/PPTX), images (with OCR), audio (with transcription), web pages (URLs), structured data (CSV/JSON/XML), and ZIP archives into AI-consumable Markdown context via MarkItDown.

OpenMetadata is a unified metadata platform for data discovery, observability, and governance. It provides a central repository for cataloging data assets across 84+ connectors, with built-in lineage tracking, data quality testing, and collaboration tools.

AgentCrew is a Python multi-agent AI framework and desktop/CLI application for building teams of specialized agents that collaborate via transfer or parallel delegation. It supports multiple model providers and tool integrations, including MCP-connected external tools, and can expose agents as HTTP services via an A2A (JSON-RPC) server.

DevDuck is a Python-based, “one-file” self-healing AI agent runtime that can hot-reload code, run many built-in tools (including shell/git/browser/messaging), and connect across multiple interfaces (CLI/TUI/WebSocket/TCP) and networks (Zenoh P2P + a unified mesh/relay). It can also expose itself as an MCP server and deploy to AWS AgentCore.

Provides a headless Ghidra server that exposes Ghidra reverse-engineering workflows to AI agents via the MCP (Model Context Protocol), with stdio (default) and TCP transports and both real (pyghidra) and fake-backend modes.

Provides a local, read-only MCP server that exposes Google Search data as relational tables via CData's JDBC Driver. The MCP server runs over stdio so an MCP-capable desktop client (e.g., Claude Desktop) can query live Google Search data using tool calls like get_tables, get_columns, and run_query (SQL SELECT).