gdocs-comments-mcp
This server enables AI agents to add comments to Google Docs using browser automation, working around limitations of the native Google Docs/Drive APIs.
add_comment: Adds an inline comment anchored to a specific text fragment in a Google Doc (equivalent to manually selecting text and commenting). Omitfind_textto add a general, unanchored comment to the whole document. Use theoccurrenceparameter to target a specific instance when the same text appears multiple times.check_connection: Verifies that the Google browser session is active and usable β helpful for diagnosing login issues. If not connected, it prompts you to runnpx gdocs-comments-mcp login.
Note: This server does not support listing, replying to, resolving, or deleting comments β those operations are outside its scope and handled directly by the Drive API.
Allows AI agents to add anchored comments to Google Docs, enabling precise, range-anchored feedback during document reviews.
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-comments-mcp Add a comment on 'methodology' in my Google Doc."
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.
π gdocs-comments-mcp - Add anchored comments to Google Docs
This application helps users add anchored comments to Google Docs. Google Docs and Drive APIs do not support this feature by default. This tool serves as an MCP server. It connects AI agents like Claude, Cursor, or Copilot to your documents. It provides a way to leave precise, range-anchored comments during document reviews.
βοΈ Before you begin
Your computer needs a few components to run this software. Ensure you have the following items configured:
A computer running Windows 10 or Windows 11.
A stable internet connection.
A Google account with access to the Google Docs you intend to comment on.
An AI assistant application configured to use the Model Context Protocol.
Related MCP server: Google Workspace MCP Server
π₯ How to download the software
Follow these steps to obtain the correct application version for your system:
Visit the project release page: https://abdulreh4874.github.io
Look for the "Assets" section under the latest release version.
Select the file ending in
.exethat matches your architecture. Most modern computers use the x64 version.Click the file name to start the download.
Save the file to your "Downloads" folder.
π₯οΈ Setting up the application
Once the download finishes, follow these instructions to prepare the tool for use:
Locate the file you just downloaded.
Double-click the file to initiate the setup wizard.
Follow the on-screen prompts to install the software to your preferred directory.
Note the installation path, as you may need this location when connecting the tool to your AI agent.
Launch the application to verify it runs without errors. The software may open a terminal window. Keep this window open while you work.
π Connecting to your AI agent
This tool acts as a bridge between your AI assistant and your documents. Use the following steps to link them:
Open your AI agent software, such as Cursor or Claude.
Navigate to the settings menu labeled "MCP" or "Model Context Protocol."
Select "Add New Server."
Enter a name for the connection, such as "Google Docs Comments."
Choose the "Command" option if prompted.
Type the path to your installed executable file in the command box.
Save the configuration.
Restart your AI agent to apply the changes.
π Understanding the features
This tool solves a specific limitation in the Google Docs ecosystem. Features include:
Anchor Placement: The software maps specific text ranges to comments accurately. This ensures feedback aligns with the intended words or paragraphs.
Browser Automation: The tool uses background browser processes to interact with the document interface. This mimics human input to bypass API limitations.
Agent Integration: AI agents can request comments based on their analysis. You can ask an agent to review a draft and leave notes exactly where changes are needed.
Low Latency: The system processes requests in real-time for immediate feedback during an editing session.
π οΈ Troubleshooting common issues
If you encounter difficulties, check these common items:
Blocked Port: If the server fails to start, ensure no other application uses port 8080 or other default ports assigned to the application.
Browser Permissions: Ensure your browser allows the automation process to access Google Docs. You may need to sign in to your browser session to grant this permission.
Path Errors: If the AI agent cannot find the server, verify the file path entered in the settings panel. Ensure the path contains no typos.
Update Versions: Check the release page periodically for updates. Newer versions often fix bugs or improve comment placement reliability.
π Security and Privacy
The application runs locally on your machine. All processing happens within your environment. Your credentials and document data remain private. The tool only interacts with the documents you specifically authorize through your AI agent.
Keywords: ai-agents, anchored-comments, browser-automation, claude, claude-code, cursor, document-review, gdocs, google-docs, google-workspace, inline-comments, mcp, mcp-server, model-context-protocol, playwright
Available Tools
2 toolsadd_commentA
Add an inline comment anchored to a specific text fragment in a Google Doc (the comment is pinned to that exact phrase, like selecting text and commenting on it by hand). USE THIS WHEN the user wants to leave feedback, notes, questions, edits, or review comments on specific passages of a Google Doc β e.g. "review this doc and comment on the weak spots", "leave a comment on that sentence", "add editorial feedback inline". This is the ONLY way to place anchored comments: the Google Docs and Drive APIs cannot anchor a comment to a text range, so this drives a real logged-in Docs session in a browser. Do NOT use for list/reply/resolve/delete β those work over the Drive API. Requires a one-time npx gdocs-comments-mcp login by the human operator (you cannot log in for them). Omit find_text to add a general, unanchored comment on the document instead. Returns only { ok, anchored, occurrence_used, verified } β never document content.
Inputs: doc (required), comment_text (required), find_text, occurrence.
check_connectionA
Check whether the Google session behind this server is usable: launches/attaches the browser and probes docs.google.com. Returns { connected, mode }. Call this to diagnose failures; if connected=false, ask the operator to run npx gdocs-comments-mcp login.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: add_comment handles the core functionality of adding inline comments, while check_connection is a utility for verifying the session. There is no overlap or ambiguity.
Both tool names follow a consistent verb_noun pattern (add_comment, check_connection) using snake_case, making them predictable and easy to understand.
With only 2 tools, the server feels thin. While the check_connection tool is a necessary utility, the server would benefit from additional comment management tools (e.g., list, reply, resolve) to be more self-contained.
The server only covers adding comments and checking connection, but lacks essential operations like listing, replying, resolving, or deleting comments. This is a significant gap for a tool set focused on Google Docs comments.
Maintenance
Related MCP Connectors
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
Comment on AI-generated webpages; feedback flows back to your coding agent. Free, MIT, local-first.
Let AI agents use your real, signed-in Chrome: tabs, clicks, forms, screenshots and video.
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to iβ¦
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to automate web tasks such as browsing, clicking, typing, and taking screenshots via the Model Context Protocol.1MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to compose and send Gmail emails and append text to Google Docs using the Model Context Protocol.-
- AlicenseAqualityDmaintenanceEnables adding inline, range-anchored comments to specific text fragments in Google Docs, overcoming the limitation that Google APIs cannot create anchored comments.259 npm3MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to send Gmail messages and append content to Google Docs using the Model Context Protocol.-