An MCP server that reads local documents and extracts text from supported file types including XLSX/XLS, DOCX, PDF, and TXT. It exposes a single MCP tool, `read_document`, which takes a file path and returns the document content.
From the registry: An MCP enabled multi-format document reader supporting DOCX, PDF, TXT, and Excel files
Please install the `mcp_documents_reader` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python** — Python 3.10 or newer is required. (https://www.python.org/downloads/)
- **Install uv** — The recommended MCP configuration uses uvx, so uv must be installed and available on PATH. (https://docs.astral.sh/uv/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["mcp-documents-reader"]
Note: README recommends installing via pip, but the simplest MCP config path shown is running the server with uvx from PyPI. No environment variables are documented.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Draw and visually collaborate with your agents on tldraw's canvas.