@dasasian/gdocs-mcp

An MCP server that lets an AI agent (like Claude Code) treat a Google Doc like a local file — read it, edit it by content, review and resolve suggestions, manage comments, and work across tabs and multiple Google accounts.

Status: beta. The tool surface is complete and every change is verified against the live API, not just unit tests. Markdown code blocks are the one construct still to render (see Roadmap).

Why this exists

Most Google Docs MCP servers treat a doc as flat text. This one fills the gap nobody else does:

• Suggestions as diffs you can act on. list_suggestions shows pending tracked-changes as before → after; apply_suggestions accepts/rejects one or more cleanly. read_doc can render them inline as <ins>/<del>.
• File-like editing. edit_doc matches a unique snippet of text (like a local Edit) and rewrites it — indices are never exposed.
• Comments. Read threads (author, quoted text, replies, resolved status), reply, resolve, add.
• Tabs as sub-files. Full create/rename/delete, and every read/edit tool can target a specific tab.
• Multiple accounts. Authorize several Google accounts; pick a default per project.

What you can ask for

You don't call tools. You ask in plain language and the agent drives them.

Fill a template without rebuilding it

"Copy the Proposal Template into /Clients/Acme, name it 'Acme Q3 Proposal', then fill in the client name, the dates, and the pricing table."

The copy keeps the letterhead, the logo at its exact size, the fonts and the page setup — everything a markdown round-trip cannot rebuild. Then only the words that change are edited. The alternative is retyping a document you already have.

A whole review pass in one instruction

"Show me the pending suggestions as a diff, accept the typo fixes, reject anything that changes meaning, then reply to the open comments and resolve the ones that are settled."

Four tools, one sentence, and the judgement in the middle is the part you wanted help with. Most Docs integrations cannot see tracked changes at all, let alone act on them safely.

More: publishing a folder of markdown as a Drive tree, auditing many docs for style drift, pulling a doc back into your repo with its images → docs/recipes.md.

Install

npm install -g @dasasian/gdocs-mcp

Or from source:

git clone https://github.com/dasasian/gdocs-mcp && cd gdocs-mcp
npm install && npm run build
npm link   # makes `gdocs-mcp` available globally, same as the published package

Then follow the setup below exactly as an installed user would. (npm link symlinks the gdocs-mcp binary to your build; see CONTRIBUTING.md for the dev workflow.)

Setup

You need a Google Cloud OAuth client (one-time). Each user creates their own — this keeps your credentials yours and avoids Google app-verification for the restricted Drive scope.

1. Create a project + enable APIs (or use the setup guide):

   gcloud projects create my-gdocs-mcp
   gcloud config set project my-gdocs-mcp
   gcloud services enable docs.googleapis.com drive.googleapis.com
   

2. OAuth consent screen (Cloud Console → APIs & Services → OAuth consent screen): User type External, add yourself as a Test user. For long-lived tokens, set publishing status to In production (avoids the 7-day refresh-token expiry).
3. OAuth client → Create credentials → OAuth client ID → Desktop app. Download the JSON and save it as ~/.config/gdocs-mcp/client_secret.json.
4. Authorize an account (opens a browser):

   gdocs-mcp add-account
   

   Repeat for each Google account you want to use.

Configure your MCP client

In a project's .mcp.json (Claude Code) or equivalent:

{
  "mcpServers": {
    "gdocs": {
      "command": "gdocs-mcp",
      "env": { "GDOCS_DEFAULT_ACCOUNT": "you@example.com" }
    }
  }
}

GDOCS_DEFAULT_ACCOUNT sets which authorized account this project uses by default — so a work project and a personal project can point at different accounts without re-authorizing. Any tool call can override it with an account argument.

Prefer it available in every project? Register once at user scope: claude mcp add gdocs -s user -e GDOCS_DEFAULT_ACCOUNT=you@example.com -- gdocs-mcp. Then a project can pin its own defaults with a .gdocs-mcp.json — both the account and a default folder for new docs:

{ "account": "work@company.com", "folder": "https://drive.google.com/drive/folders/…" }

With a folder set, create_doc files new docs there automatically (an explicit folder argument still overrides). See docs/setup.md for the full resolution order.

You don't have to edit that file by hand — just tell the agent "make damithsc@gmail.com my default account for this project" or "make my Manuscripts folder the default here," and it writes the .gdocs-mcp.json for you via set_project_default (searching for the folder by name if needed).

Tools

The table below is the reference. For what to actually ask for, see What you can ask for above, or the full set in docs/recipes.md.

Every doc tool accepts an optional account (override the default) and, where relevant, a tab (target a tab by id or title).

Drive as a filesystem

Drive navigation is one tool speaking shell, because the model already knows shell. Arguments are positional and differ per command, exactly as they do in a terminal.

{ "cmd": "ls",    "args": ["/Work/2026"] }
{ "cmd": "find",  "args": ["quarterly report", "-type", "d"] }
{ "cmd": "mkdir", "args": ["-p", "/Work/2027/Q1"] }
{ "cmd": "cp",    "args": ["/Work/Template", "/Work/2027/Q1/Report"] }
{ "cmd": "mv",    "args": ["/Work/Roof", "/Archive"], "expectName": "Roof" }

Flags and operands parse in any order (cp -r a b, cp a b -r, cp a -r b), and -- ends the options.

Three places Drive is not a filesystem. The vocabulary is borrowed only where it is honest, and refuses where it is not:

• Two files may share a name in one folder, and matching folds case. No filesystem the model learned from does either, so it would not think to check. A path matching more than one thing is refused with the candidates listed, never guessed — and cp/mv refuse to create that state too, rather than manufacturing an ambiguity the resolver would then decline to resolve.
• cp -r does not exist. Drive's files.copy refuses folders (its own web UI cannot copy one either), so cp on a folder explains that rather than half-working.
• mv into /shared/… gives the file away. Shell mv across filesystems leaves you owning the file; moving into a shared drive transfers ownership to that organization and cannot be undone from your side. It requires acceptOwnershipTransfer: true.

Paths see less than find does. A file with no parent still opens and still turns up in a search, but no path can name it — nothing that browses the tree will ever show it. find is the complete view; /lost+found is where those files surface.

There is no rm. See #47.

Known limitations

These are Google-API constraints, not bugs — the highlights are below; the complete reference (with the API reason and the workaround for each) is in docs/limitations.md.

• Can't create suggestions. No API writes in suggestion mode — every edit is direct (live text). apply_suggestions only resolves existing ones. Tools that write say so.
• No suggestion attribution (author/timestamp) — suggestions are listed in document order.
• Comments created via the API aren't anchored to text, and Drive returns author name only (no email).
• Images are inline only (no floating/x,y positioning), and Google downscales/re-encodes embedded images, so pulled copies aren't byte-identical.
• Headers and footers are separate content trees — not part of the body. Every content tool (read_doc, edit_doc, set_style, get_style, insert_content, insert_image, insert_table, edit_table, set_table_style, list_suggestions, apply_suggestions) takes segment: "header" | "footer" to reach them, and page when a doc defines more than one.
• Markdown can't express computed style (spacing, fonts, colors) or deep table styling — read it with get_style, set it with set_style/set_table_style. Code blocks aren't rendered from markdown yet (roadmap).

See docs/limitations.md for the full table, including how each is mitigated or surfaced.

Roadmap

• Code blocks in the markdown writer — the remaining Tier-2 block type (tables and images already render; standalone insert_table / insert_image tools exist too).

Suggestion attribution (author/timestamp) is not on the roadmap — it has no API path for typical suggestions (see docs/limitations.md).

The "manuscript sync" use case (chapter files ⇄ tabs, reviewing suggestions, merging) is intentionally not a server feature — an AI agent orchestrates it over these primitives. See DESIGN.md §10b.

Development

npm install
npm run build      # tsc
npm test           # vitest
npm run typecheck

See DESIGN.md for the full architecture and the empirical findings behind it.

Acknowledgements

Architecture and approach informed by prior open-source Google Docs MCP servers — notably @a-bonus/google-docs-mcp and taylorwilsdon/google_workspace_mcp.

License

MIT © Dasasian