The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Google Docs listing page.
MCP server for Google Docs - read and edit documents.
Document Q&A: "What does the contract say about termination clauses?" → reads the doc and pulls out the relevant section.
Meeting-to-doc workflow: After a call, reads the Gemini transcript plus follow-up Slack discussion, then updates your team charter with the decisions made.
Release announcement: "Draft a blog post about the new feature based on the GitHub PRs and Slack discussions in #proj-awesome" → synthesizes technical changes into user-facing content.
Daily planning with persistent context: Your AI assistant reads a "planning log" doc at the start of each day, asks about yesterday's progress, helps you identify today's priority, then updates the doc with your plan. Context carries over across sessions - it remembers what you said you'd do and can follow up.
(These are just examples - any workflow that needs document reading or editing can use this. Use in combination with google-drive-mcp for finding files, deleting, comments, and sharing permissions.)
http://localhost:3000/callback to Authorized redirect URIsThe server runs on http://localhost:3000 by default. Change with PORT=3001.
With the server running, follow the instructions on install-mcp, which generates the right config for your MCP client (Claude Code, Claude Desktop, Cursor, Cline, VS Code, and more).
This server acts as an OAuth proxy to Google:
/.well-known/oauth-authorization-server/register returns the Google OAuth client credentials/authorize redirects to Google, encoding the client's callback URL in state/callback receives the code from Google and forwards to the client's callback/token proxies token requests to Google, injecting client credentials/mcp handles MCP requests, using the bearer token to call Google Docs APIThe server holds no tokens or state - it just proxies OAuth to Google.
| Tool | Description |
|---|---|
document_get_raw | Get full raw JSON structure (all tabs, formatting, headers, footers, styles) |
document_get_text | Get plain text content of all tabs |
document_create | Create a new blank document |
document_batch_update | Apply multiple edits atomically (insert, delete, format, etc.) |
document_append | Append text to end of document |
document_insert | Insert text at a specific index |
document_replace | Find and replace text |
The document_batch_update tool supports these operations:
insertText - Insert text at a locationdeleteContentRange - Delete a range of contentreplaceAllText - Find and replace all occurrencesinsertInlineImage - Insert an imageinsertTable - Create a tableinsertTableRow / insertTableColumn - Add rows/columns to tablesdeleteTableRow / deleteTableColumn - Remove rows/columns from tablesinsertPageBreak - Add a page breakcreateNamedRange / deleteNamedRange - Manage named rangescreateParagraphBullets / deleteParagraphBullets - Manage bullet listsdocuments - Full access to read and edit documentsPull requests are welcomed on GitHub! To get started:
npm installnpm run test to run testsnpm run buildVersions follow the semantic versioning spec.
To release:
npm version <major | minor | patch> to bump the versiongit push --follow-tags to push with tags