context-mode: Every tool call in an MCP (Model-Controller-Program) environment dumps raw data into the context window, quickly consuming space and causing the agent to lose track of ongoing tasks. Context Mode is an MCP server that tackles this by sandboxing tool outputs to significantly reduce context usage, tracking session events in SQLite for continuity, and promoting 'think in code' to minimize data processing within the LLM.; wechat-local-mcp: WeChat Local MCP is a local data server that reads WeChat 4.x chat history, contacts, groups, and media files via the Model Context Protocol. It provides 25 MCP tools with cache-first indexing and agent-friendly installation on macOS and Windows. Ideal for AI agents like Claude Code, Codex, and Cursor to access personal WeChat data.
Deep repository research and analysis (e.g., architecture, contributors, issues)
Read local WeChat chat history, contacts, groups, media files, and Moments