Latest insights, tutorials, and updates from the Model Context Protocol team
paperclip is an open-source TypeScript MCP Client for managing AI agents within an organizational structure. It allows developers to integrate any agent, track costs, and enforce governance, solving the challenge of deploying and overseeing AI workforces at scale.
next-ai-draw-io enables AI agents to draw and edit draw.io diagrams through chat. This MCP Client integrates directly with tools like Claude Desktop, Cursor, and VS Code, allowing developers to generate and modify complex diagrams using natural language. It streamlines diagram creation and editing within existing AI-powered workflows.
browser-use is a Python library and cloud service for AI browser agents, offering stealth browsers and a hosted agent API. It solves the problem of programmatic web interaction for AI, making it a key MCP Client for developers building intelligent automation.
context-mode is an MCP Client for AI coding agents that optimizes context windows, achieving a 98% reduction in sandboxed tool output. It addresses a critical context problem for developers building AI-driven coding solutions across 15 platforms.
Scrapling is an adaptive Python-based MCP Server for web scraping, offering a full crawling framework with Scrapy-like APIs. It solves the problem of robust, scalable data extraction from the web, making it ideal for developers building AI agents that require real-time or persistent data feeds.
dbx is a 20 MB cross-platform database client supporting over 70 databases. It provides a separate Rust-powered MCP server, enabling AI coding agents to securely query databases using pre-configured connections and managed access policies. Developers can integrate dbx with tools like Claude Code to facilitate AI-driven database interactions.