Packages

MCP Gearbox from GPTScript-AI — a tool aggregation and routing layer for MCP that combines multiple MCP servers into a unified interface, manages MCP tool lifecycles, and provides a single connection point for AI agents to access tools from multiple underlying MCP servers. Simplifies multi-MCP deployments by acting as a composable middleware layer.

MCP server providing formal logic and reasoning capabilities to AI agents. Enables agents to execute Prolog-style logical inference, validate logical constraints, perform knowledge base queries, and use formal logic for verification and reasoning tasks — extending LLM capabilities with symbolic reasoning.

MCP server enabling AI agents to send Apple Events — the macOS inter-application communication protocol used by AppleScript. Allows agents to automate macOS applications (Finder, Mail, Calendar, Safari, etc.) by sending Apple Events programmatically, enabling system-level macOS automation from AI agents.

Node.js Debugger MCP server enabling AI agents to debug Node.js applications — connecting to Node.js debug protocol, setting breakpoints, stepping through execution, inspecting variables and call stacks, and integrating Node.js debugging into agent-driven JavaScript/TypeScript development and troubleshooting workflows.

Official Redis Cloud MCP server enabling AI agents to manage Redis Cloud subscriptions and databases — creating databases, monitoring usage, managing access, and configuring Redis Cloud infrastructure.

Official ScrapeGraph MCP server providing AI-powered web scraping and structured data extraction — using LLMs to extract structured information from web pages without brittle CSS selectors.

MCP server for generating UML diagrams programmatically, typically using PlantUML or similar tools. Enables AI agents to create UML diagrams from text descriptions — class diagrams, sequence diagrams, activity diagrams, component diagrams — and render them as images for documentation and architecture visualization.

Windows CLI MCP server enabling AI agents to execute commands in Windows Command Prompt and PowerShell — running CMD scripts, executing PowerShell commands, managing Windows system operations, and integrating Windows command-line capabilities into agent-driven Windows automation and development workflows.

High-performance MCP server for Obsidian providing AI tools with direct vault access through semantic operations, graph navigation, fuzzy text matching, Dataview query execution, and HTTP transport for network-based integration.

MCP server that exposes Chrome DevTools Protocol (CDP) capabilities to AI agents, enabling agents to attach to Chrome browser sessions, inspect DOM elements, capture network traffic, execute JavaScript in page context, take screenshots, and perform debugging operations through structured MCP tool calls.

An MCP server that enables AI assistants to discover and use Claude Agent Skills through semantic search with vector embeddings, bridging Anthropic's Skills framework to any MCP-compatible application.

Discord MCP server enabling AI agents to interact with Discord — reading and sending messages in channels, managing server members, creating and managing roles, posting to channels, and integrating Discord's community platform into agent-driven community management, notification, and automated moderation workflows.

MCP server wrapping Google's Gemini AI API. Enables AI agents to call Gemini models for text generation, multimodal analysis (text + images + video), code generation, and reasoning tasks. Provides a standardized MCP interface to Gemini's capabilities including Gemini Pro, Ultra, and Flash model variants.

MCP server that bridges Language Server Protocol (LSP) servers (gopls, rust-analyzer, pyright, etc.) to AI clients, giving LLMs semantic code navigation — go-to-definition, find references, diagnostics, hover docs, and rename symbol — instead of naive text search.

MCP Sandbox enabling AI agents to execute code in isolated sandboxed environments — running Python and other code safely in Docker containers, capturing output, preventing filesystem and network access, and integrating safe code execution into agent-driven development and data analysis workflows without local system risk.

MCP server by prolific Office-integration developer GongRzhe enabling AI agents to create and manipulate Microsoft Visio diagrams — generating flowcharts, network diagrams, org charts, process flows, and other visual diagrams programmatically. Allows agents to produce Visio files from structured data or natural language descriptions.

MCP server providing AI agents with access to Storybook — the component development environment used by most frontend teams. Enables agents to browse component stories, read component documentation, inspect component props and variants, and reference design system components when generating or reviewing UI code.

DINO-X MCP server from IDEA Research enabling AI agents to perform universal object detection and visual grounding — detecting any objects in images using open-vocabulary detection, grounding object descriptions to bounding boxes, and integrating DINO-X's state-of-the-art vision capabilities into agent-driven image analysis workflows.

Debug Adapter Protocol (DAP) MCP server enabling AI agents to control debuggers via the Debug Adapter Protocol — setting breakpoints, stepping through code, inspecting variables, evaluating expressions in debug context, and integrating AI-assisted debugging into development workflows. Supports any DAP-compatible debugger (VS Code debug adapters, gdb, lldb, etc.).

MCP server from Descope (descope-sample-apps org) for their authentication and user identity platform. Enables AI agents to manage users, handle authentication flows, query audit logs, and interact with Descope's identity management capabilities — supporting AI-driven user management and security monitoring workflows.