Packages

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.

Expo's push notification service that abstracts FCM and APNs into a single API, enabling cross-platform push notifications for React Native apps built with Expo.

Google's scalable, serverless NoSQL document database with real-time sync, offline support, and a REST API, designed for mobile and web app backends.

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.

Container orchestration platform API that manages deployment, scaling, and operation of containerized applications across clusters, providing a REST API for all cluster management operations.

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.

Phone MCP server enabling AI agents to control Android devices via ADB (Android Debug Bridge) — launching apps, taking screenshots, simulating taps and swipes, executing shell commands, installing/uninstalling APKs, capturing device logs, and integrating Android device control into agent-driven mobile testing and automation workflows.

Visual bookmark manager and content curation tool with REST API — enabling users to save, organize, and rediscover web content with visual previews, tags, collections (folders), full-text search, PDF and image saving, team collaboration on shared collections, and public collection sharing, with a clean API for bookmark management integrations.

Remote MCP proxy server enabling AI agents to access MCP servers running on remote machines over the network — acting as a relay between a local MCP client and a remote MCP server, enabling centralized deployment of MCP servers that multiple agents or clients can share without local installation.

SDL MCP server enabling AI agents to work with SDL (Simple DirectMedia Layer) — the cross-platform multimedia library for C/C++ game and application development — providing SDL API documentation and code examples, generating SDL initialization code, managing SDL windows and rendering contexts, and integrating SDL development assistance into agent-driven game and multimedia application workflows.