google-docs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_CLIENT_ID | No | Google OAuth client ID (alternative to GOOGLE_OAUTH_CREDENTIALS) | |
| GOOGLE_CLIENT_SECRET | No | Google OAuth client secret (alternative to GOOGLE_OAUTH_CREDENTIALS) | |
| GOOGLE_OAUTH_CREDENTIALS | No | Path to the OAuth client JSON file (default: ~/.config/google-docs-mcp/credentials.json) | |
| GOOGLE_DOCS_MCP_CONFIG_DIR | No | Base directory for the two files above (default: ~/.config/google-docs-mcp) | |
| GOOGLE_DOCS_MCP_TOKEN_PATH | No | Path where the user's tokens are stored (default: ~/.config/google-docs-mcp/token.json) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_auth_statusA | Check whether the server is signed in to Google and which account is being used. Call this first if other tools fail with authentication errors. |
| list_documentsA | Search the user's Google Drive for Google Docs documents (including shared drives). Returns name, ID, owner and last-modified date, newest first. Use the returned ID with the other tools. |
| get_documentA | Read a Google Doc: metadata (title, owner, last modified) and its plain-text content across all tabs. Useful to understand what the comments refer to. |
| list_commentsA | List the comments of a Google Doc in full detail: author, dates, open/resolved status, the quoted text each comment refers to, every reply in the thread (with who resolved or reopened it) and, optionally, the surrounding paragraph of the document. This is the main tool of this server. |
| get_commentA | Fetch one comment of a Google Doc by ID with its full reply thread, quoted text and surrounding paragraph. |
| get_comments_summaryA | Aggregate view of all comments in a Google Doc: counts by status, participants and their activity, open comments with no replies, open comments waiting for the original author, oldest open comment and latest activity. Reads every page of comments. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
The tools separate cleanly by resource and granularity: auth, document discovery, document content, and comment retrieval. The three comment tools overlap somewhat, but full-detail listing, single-comment retrieval, and aggregate summary are distinct enough from their descriptions.
All tools follow a consistent snake_case verb_noun pattern using get_ or list_. Collection retrieval uses list_, single-resource retrieval uses get_, and the aggregate tool is still clearly named as a summary.
Six tools is well-scoped for a read-focused Google Docs and comments server. Each tool serves a distinct step in the workflow without unnecessary redundancy.
The read/comments-analysis surface is nearly complete: auth, document discovery, document contents, full comment threads, and summary analytics are all covered. The only gap is the absence of write or comment-management operations, which matters if the server is expected to be a full Google Docs MCP rather than a read-only one.