Connect Google Docs to Claude Code
Let Claude write, restructure, and comment inside your Google Docs. From the terminal, inside the sessions where you already work.
How do you connect Google Docs to Claude Code?
Claude Code reaches outside tools through MCP servers. To connect Google Docs, you add a Google Docs MCP server: a small hosted service that exposes Google Docs's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Google Docs account. No API keys pasted into config files.
claude mcp add --transport http google-docs https://your-connector-url/mcpThen run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.
What can Claude Code do in Google Docs once connected?
Full read-write Google Docs access lets Claude insert or replace text in a document, restructure headings and lists, apply basic formatting, leave comments for review, and create a new doc from a draft. The writing and cleanup that used to mean copying into a chat window happen where the document already lives.
- Insert or replace text in a specific section of an existing document
- Create a new document from an outline or draft
- Restructure headings, lists, and sections for a cleaner flow
- Apply basic formatting like bold, headings, and bullet points
- Leave comments on a passage for a teammate to review
- Find every doc matching a query and propose consistent edits
One connector, every Claude surface
The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Google Docs access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.
Build it yourself, or have it built?
If you live in the terminal, you can absolutely write your own MCP server against the Google Docs API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Google Docs changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Google Docs connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.
Frequently asked questions
Does the same Google Docs connector work in claude.ai and Claude Code?
Do I need to host or maintain anything myself?
Is it safe to give a coding agent write access to Google Docs?
More on the Google Docs connector
Tell us what you run. We'll build the connector.
Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.
