zk-doc-mcp-server

# ZK Documentation MCP Server An [MCP (Model Context Protocol) server](https://modelcontextprotocol.io/docs/learn/server-concepts) for the [ZK Framework documentation](https://github.com/zkoss/zkdoc) that provides semantic search, intelligent Q&A, and documentation indexing capabilities. ## Overview This server integrates [Chroma](https://docs.trychroma.com/docs/overview/introduction) for vector-based semantic search and implements MCP tools for searching [ZK documentation](https://github.com/zkoss/zkdoc). You can use this MCP server with any AI tool that supports MCP servers to: - Retrieving specific documentation content - Answering questions based on ZK documentation - Managing documentation indices - Submit your feedback aboutZK documentation ## Quick Start ### Prerequisites Your environment should have the following installed: - Python 3.10 or higher. - `uv` package manager (https://docs.astral.sh/uv/) - optional but recommended - **Git** (2.7 or higher) - Required for cloning ZK documentation from the Github repository ### Installation zk doc MCP server from PyPI create a virtual environment of Python 3.10 ```bash uv venv --python 3.10 ``` ```bash # Using uv (recommended) uv pip install zk-doc-mcp-server # This command installs the package into the currently active virtual environment. ``` List installed package to check ```bash uv pip list ``` Upgrade it if you installed an older version ```bash uv pip install --upgrade zk-doc-mcp-server ``` The package is available at [PyPI](https://pypi.org/project/zk-doc-mcp-server/) ### Initialize Documentation (Optional Setup) After installation, you can optionally pre-index the ZK documentation for faster server startup: ```bash uvx zk-doc-mcp-server init ``` This command: 1. **Clones/syncs** the documentation repository to `ZK_MCP_SRC_DIR` 2. **Pre-indexes** the documentation for semantic search After running `init`, subsequent server startups can be immediately ready for doc search. Otherwise, you mi…