Google Drive MCP integration for AI agents | Unblocked

Google Drive integration details

Category

Knowledge

Indexed data

• Google Docs
• Google Sheets
• Google Slides
• text files
• PDFs
• folders
• shared drives

Supported products

• Google Drive
• Google Drive for Workspaces

Works with

• Claude Code
• Cursor
• Windsurf
• GitHub Copilot
• Codex
• OpenCode
• VS Code — via one MCP server connection

Content reviewed

July 20, 2026

What the Google Drive integration adds

Product requirements, architecture proposals, launch plans, and runbooks often live in Google Drive rather than the repository. Unblocked makes the Drive content you select discoverable in the same research path as code and issue history, with a link back to the source document.

Instead of treating document search as a separate task, an agent can use a design doc to explain the intent behind an implementation, compare a pull request with its requirements, or find the operational procedure related to an incident.

Teams that need organization-wide coverage can use Google Drive for Workspaces to connect current and future Workspace content while retaining document-permission awareness. This uses a separate Google administrator setup from the individual Google Drive connection.

Through the Unblocked MCP integration, Google Drive context is available to Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, VS Code, and other compatible AI coding tools.

What you get

• Searchable Google Drive context — Bring selected Google Docs, Sheets, Slides (including speaker notes), plain-text files, and PDFs into the same cited research workflow as source code, pull requests, and issue history.
• Files, folders, and shared drives — Grant access at the file, folder, or shared-drive level to match how your team organizes its documentation.
• Google Drive for Workspaces — Support an organization-wide content scope with document-permission awareness and optional access to personal Drive content when Data Shield is enabled.
• Managed access — The connecting user adds files and any admin can remove them, so you keep control over what Unblocked can reference.
• Cross-source synthesis — Drive documents are combined with your code, pull requests, Jira tickets, and Slack threads into a single knowledge graph.

How to connect Google Drive to Unblocked

Prerequisites

• An Unblocked account (free to start).
• A Google account with access to the files, folders, and shared drives you want to index.
• For Google Drive for Workspaces, a Google Super Admin or delegated custom admin must complete the organization-level setup.
• An MCP-compatible coding agent (Claude Code, Cursor, Windsurf, etc.) to use the context in your editor.

Step 1: Connect Google Drive to Unblocked

1. In Unblocked, go to Settings → Data Sources → Connect another data source, and under Documentation select Google Drive.
2. Confirm you want to share your Drive files, then sign in to Google and authorize Unblocked.
3. Choose the files, folders, and shared drives you want Unblocked to reference.
4. Click Save Settings — Unblocked begins using these resources to answer questions.

Step 2: Install the Unblocked MCP server

On macOS or Linux, one command auto-detects and configures your supported agents (Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, OpenCode, VS Code):

curl -fsSL https://getunblocked.com/install-mcp.sh | bash

On Windows, or when you prefer remote MCP, add the server manually using the configuration below.

Claude Code

Add the remote server, then run /mcp in Claude Code, select unblocked, and log in via OAuth:

claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsse

Cursor

Open View: Open MCP Settings → Add Custom MCP, add the server, then click Connect to authenticate via OAuth:

{
  "mcpServers": {
    "unblocked": {
      "url": "https://getunblocked.com/api/mcpsse"
    }
  }
}

Other MCP clients

Any MCP-compatible client (Windsurf, Codex, VS Code, Claude Desktop, and others) can connect to the remote server with OAuth:

https://getunblocked.com/api/mcpsse

Connect Google Drive to Claude Code, Cursor, and other AI agents

To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to Google Drive context, connect Google Drive to Unblocked and add the single Unblocked MCP server to your agent.

Unblocked acts as the MCP context layer for your Google Drive data, searching Google Docs, Google Sheets, Google Slides, text files, PDFs, folders, shared drives alongside your other connected sources and returning cited results through these tools:

• context_research Multi-source research across your Google Drive documents, plus your code, pull requests, and other connected sources. Returns a synthesized answer with citations back to the document it used.
• context_get_urls Fetches the full content behind a Google Drive document URL your agent encounters — plus GitHub, Jira, Linear, Confluence, Slack, and more.

Questions to ask an AI agent about Google Drive

Questions you (or your agent) can ask Unblocked about your Google Drive data:

• What does the design doc in Drive say about our caching strategy?
• Where is the launch checklist for the mobile release?
• What are the requirements captured in the product PRD?
• Which document describes our data-retention policy?