Packages

MCP server for generating and managing Product Requirements Documents (PRDs). Enables AI agents to create structured PRDs from product ideas, retrieve PRD templates, update requirement sections, and manage product documentation — supporting AI-assisted product management and technical writing workflows.

A hybrid SAST and dead code detection tool for Python, TypeScript, and Go that combines AST-based static analysis with optional LLM-powered remediation, offering framework-aware false-positive reduction and CI/CD integration.

WordPress MCP server enabling AI agents to interact with WordPress sites via the WP REST API — reading and creating posts and pages, managing categories and tags, querying media library, handling comments, and integrating WordPress's CMS capabilities into agent-driven content creation, site management, and publishing automation workflows.

MCP server for Abstract Syntax Tree (AST) analysis of source code. Enables AI agents to parse source code into ASTs, query code structure, extract function definitions and class hierarchies, analyze code patterns, and perform structural code analysis — supporting AI-driven code understanding and refactoring workflows.

Apache Spark History Server MCP enabling AI agents to query the Spark History Server — retrieving completed and running Spark job metadata, execution timelines, stage details, and task metrics — integrating Spark's job monitoring into agent-driven data engineering observability and pipeline debugging workflows.

Blockbench MCP plugin enabling AI agents to interact with Blockbench — the popular free 3D modeling editor for Minecraft and voxel game assets — creating and modifying 3D models, managing textures and UV maps, exporting models in various game formats (Bedrock, Java, OBJ), and integrating AI-driven 3D asset creation into Minecraft modding and game development workflows.

MCP server for Browserbase cloud browser automation — enables AI agents to automate cloud-hosted browsers to navigate websites, interact with elements, and extract data. Provides scalable headless browser infrastructure for AI-driven web automation without managing local browser infrastructure.

Personal context management MCP server from Autoblocks AI — enabling AI assistants to store, retrieve, and manage personal context for more personalized and consistent interactions. Allows AI agents to remember preferences, facts, and patterns about users across sessions through a context management layer.

A Python SDK for building MCP servers with progressive tool disclosure. Instead of exposing all tools at once, it organizes them into workflow stages and reveals only contextually relevant tools at each step. Supports semantic search mode that collapses 100+ tools into two meta-tools (search_tools and call_tool).

An MCP server that enables AI agents to create, read, and modify Excel files without requiring Microsoft Excel. Supports formulas, formatting, charts, pivot tables, data validation, conditional formatting, and sheet management. Built on openpyxl with stdio, SSE, and streamable HTTP transport options.

A Python framework for building production-ready MCP servers with minimal boilerplate. Provides automatic tool/prompt/resource discovery from directory structure, enterprise-grade auth (JWT, OAuth 2.0, API keys), OpenTelemetry tracing, built-in LLM utilities, and a CLI for project scaffolding and development.

Home Assistant MCP server enabling AI agents to interact with Home Assistant — the popular open-source home automation platform. Enables querying device states (lights, sensors, thermostats, locks), controlling smart home devices, reading automation status, triggering scenes, and integrating home automation data into AI-assisted home management workflows.

InfoBus MCP server providing a message bus and event system for AI agents — enabling agents to publish messages to topics, subscribe to events, broadcast information across agent networks, and coordinate between multiple agents via an asynchronous message passing architecture integrated with the MCP protocol.

Knowledge Base MCP server enabling AI agents to interact with a structured knowledge base — creating, reading, updating, and searching knowledge articles, managing categories and tags, indexing documentation for semantic search, and integrating organizational knowledge into agent-driven information retrieval and content management workflows.

MATLAB MCP server enabling AI agents to interact with MATLAB — the industry-standard numerical computing and simulation environment from MathWorks. Enables executing MATLAB code, running simulations, calling MATLAB functions, reading workspace variables, processing numerical data, and integrating MATLAB's powerful engineering and scientific computing into AI agent workflows.

MCPDocSearch MCP server enabling AI agents to search documentation sites — crawling and indexing documentation from any URL, performing semantic search over indexed docs, and integrating documentation search into agent-driven coding, research, and knowledge management workflows.

MCPJungle is a self-hosted MCP gateway that aggregates multiple MCP servers behind a single endpoint, enabling AI clients and agents to access all registered tools through one connection with canonical tool naming.

MetaTrader 5 MCP server enabling AI agents to interact with MetaTrader 5 — the industry-standard trading platform — accessing real-time and historical market data, querying account positions, analyzing technical indicators, and integrating MT5's comprehensive trading environment into agent-driven financial analysis workflows.

Community MCP server for NPM package security analysis — enabling AI agents to check npm packages for vulnerabilities, inspect package metadata, audit dependencies, and get security insights from the npm registry.

Osaurus is an always-on AI edge runtime for macOS that runs local models via MLX on Apple Silicon or routes to cloud providers (Anthropic, OpenAI, xAI, Ollama), exposing both OpenAI-compatible and Anthropic-compatible APIs alongside a built-in MCP server for agent tool access.