Allows reading, editing, appending, and rewriting content in Google Docs while preserving styles, as well as debugging document styles.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@gdocs-mcp-server Read my latest planning document"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server for reading and editing Google Docs.
read_document — read the full text content of a Google Doc
edit_document — replace the full content of a Google Doc
append_to_document — add content to the end of a Google Doc
insert_after_heading — insert content after a named heading
style_preserving_rewrite — rewrite a doc's content while preserving its existing paragraph/text styles
debug_styles — dump the raw, unprocessed per-paragraph style data for a doc, straight from the Docs API
Related MCP server: Google Docs MCP Server
Create a Google Cloud project, enable the Google Docs API, and create an OAuth 2.0 Client ID
(Desktop app type). Download the client secret JSON and save it in this directory as
credentials.json.
Install dependencies into a virtualenv:
python3 -m venv venv
./venv/bin/pip install -r requirements.txtRun the one-time auth flow to generate token.json:
./venv/bin/python auth.pyPoint your MCP client at server.py (e.g. via ./venv/bin/python server.py).
credentials.json and token.json are gitignored — never commit them, they grant access to
your Google account.
This server cannot be deployed
Share HTML/Markdown documents via URL instantly. Create, edit, delete docs from any AI tool.
Provides tools for searching Google Workspace documentation and much more.
Google Docs MCP Pack — read, create, and edit Google Docs via OAuth.
Composable APIs for document extraction, image transformation, and document & sheet generation.
