Latest insights, tutorials, and updates from the Model Context Protocol team
PostHog is a Python-based MCP Client designed for building self-driving products. It provides AI observability, analytics, and developer tools to capture context for diagnosing problems and shipping fixes, steerable via MCP, Slack, web, or desktop.
siyuan is a privacy-first, self-hosted personal knowledge management (PKM) MCP Client written in TypeScript and Go. It solves the problem of managing extensive knowledge bases with block-level linking, AI Q&A, and robust export, ideal for developers seeking a powerful, open-source solution.
opik is an open-source MCP Server for LLM evaluation, tracing, and monitoring. Built by Comet, it helps developers improve RAG chatbots, code assistants, and agentic pipelines with features like LLM-as-a-judge metrics and CI/CD integration. Use opik to build better, faster, and cheaper LLM systems.
AIHawk is an open-source AI browser agent that automates web browsing and computer use in plain English. It integrates as an MCP Client, enabling direct control from Claude Code and Gemini CLI for tasks like job applications or data fetching.
hyperframes is an MCP Client for AI agents, written in TypeScript, that enables the generation of video content from HTML. It specifically targets agents that need to produce visual output, offering a structured way to render dynamic video.
Douyin_TikTok_Download_API offers a self-hosted Python MCP Server for scraping Douyin and TikTok, downloading no-watermark videos, and archiving content. It solves the problem of platform data collection and media preservation with an identity pool, PostgreSQL archive, and one-command Docker deployment. Developers needing robust, self-managed access to TikTok/Douyin data via MCP will find it useful.