What Can It Do?
- Search documents in Google Drive by keyword
- Read document content including body text, lists, images, footnotes, headers, footers, and styles
- Create new documents with plain text, Markdown, or HTML content
- Update existing documents by appending, prepending, replacing, or inserting content
- Manage tables by inserting new tables and updating individual cells
- Navigate multi-tab documents by listing and reading individual tabs
Where to Use It
In Agents (Recommended)
Add Google Docs as a tool to any agent. The agent can then search and edit your documents conversationally, choosing the right actions based on context. To add an MCP tool to your agent:- Open your agent’s configuration
- Click Add tools → Connect an app with MCP
- Search for the integration and select it
- Authenticate with your account
In Workflows (Via Agent Node)
For automated pipelines, use an Agent Node with Google Docs tools. This gives you the flexibility of an agent within a deterministic workflow.As a Custom MCP Node
You can also create a standalone MCP node for a specific action. This generates a reusable node that performs one task, useful when you need the same operation repeatedly in workflows.- Go to your node library and search for the integration
- Click Create a node with AI
- Describe the specific action you want (e.g., “Read the full content of a Google Doc”)
- Test the node and save it for reuse
Custom MCP nodes are single-purpose by design. For tasks that require multiple steps or dynamic decision-making, use an agent instead.
Available Tools
Read Tools
| Tool | Description |
|---|---|
| Search Docs | Search for Google Docs in Drive by keyword |
| Read Doc | Read content from a Google Doc including body, lists, inline objects, footnotes, headers, footers, and styles. Supports reading specific tabs in multi-tab documents |
| List Tabs | List all tabs in a Google Doc with their IDs and titles |
Write Tools
| Tool | Description |
|---|---|
| Create Doc | Create a new Google Doc with content in plain text, Markdown, or HTML format |
| Update Doc | Update content in an existing Google Doc. Supports append, prepend, replace, insert at index, and find-and-replace operations. Content can be plain text, Markdown, or HTML |
| Insert Table | Insert a table into a Google Doc with optional data and header styling |
| Update Table Cell | Update the content of a specific table cell |
Create Doc and Update Doc support a
content_format parameter with three options: plain (default), markdown (CommonMark), and html (rich formatting including bold, italic, colors, headings, lists, tables, code blocks, and images). When using Markdown or HTML, manual style parameters are ignored.Example Prompts
Use these with your agent or in the Agent Node: Search for documents:Troubleshooting
| Issue | Solution |
|---|---|
| Agent not finding the right document | Use specific document titles or IDs |
| Action not completing | Check that you’ve authenticated and have edit access to the document |
| Unexpected results | The agent may chain multiple tools (e.g., searching first, then reading content). Review the agent’s reasoning to understand its approach. |
| Tool not available | Verify the tool is enabled in your agent’s MCP configuration |
| Rich text not rendering | Make sure to set content_format to markdown or html when using formatted content |
Need Help?
- Agents documentation for setup and best practices
- Agent Node guide for workflow integration
- Gumloop Community for questions and examples
- Contact support@gumloop.com for assistance
Use this integration directly in Claude or Cursor. Connect remotely via the Google Docs MCP server using your Gumloop credentials.