Arezzo is an MCP server for Google Docs that reads document structure and compiles high-level edit operations into correct Google Docs `batchUpdate` request sequences. It handles UTF-16 indexing, cascading index shifts, and supported edits like text changes, formatting, tables, lists, images, headers/footers, footnotes, and named ranges.
From the registry: Deterministic Google Docs API compiler. Your agent stops silently corrupting documents.
$ pip install arezzo$ arezzo initPlease install the `arezzo` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Arezzo Python package** — Install the MCP server package from PyPI. Run: `pip install arezzo`
- **Create a Google Cloud project and enable Google Docs API** — Set up a Google Cloud project with the Google Docs API enabled.
- **Create Google OAuth 2.0 desktop client credentials** — Create an OAuth 2.0 client ID of type Desktop application and obtain your credentials.json file.
- **Run Arezzo initialization** — Run the setup wizard once to copy credentials.json to ~/.config/arezzo/, complete the browser-based OAuth consent flow, and generate MCP client config files or print the manual config block. Run: `arezzo init`
Canonical MCP server config (stdio transport):
- command: `arezzo`
- args: []
Note: The README shows generated client-specific wrapper JSON, but the canonical MCP configuration is simply the stdio command `arezzo` with no args or env vars documented. Authentication is handled by the one-time `arezzo init` flow rather than config-file environment variables.
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.Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.