A plug-and-play MCP toolkit providing AI agents with web search (Chinese sources prioritized), file operations, and shell command execution capabilities.
Enables AI agents and MCP clients to search, retrieve, and read documents across unified knowledge sources including ShowDoc, GitHub, Gitee, ZenTao, Evernote, and Tencent Docs. It also supports connecting external MCP servers as additional knowledge sources.
Enables AI tools to search and manage a private local knowledge base via MCP or HTTP, using local Chinese semantic retrieval without sending data externally.
Enables users to index and retrieve local documents through semantic, BM25, or hybrid search, with tools for chunk reads and page images accessible from MCP clients such as Codex and ChatGPT web.
Enables Chinese-language AI agent developers to register, discover, and invoke tools over the Model Context Protocol, with built-in demos for GB building-code lookup, A-share trading-signal analysis, and content-safety auditing. It also supplies CLI scaffolding for new skills, hot-loaded sandboxed plugins, and tool pre-filtering with context compression to cut token overhead.
Enables AI agents to save, search, and manage local Chinese semantic memories on demand, with support for updating, merging, and Obsidian-style linking.