Skip to content
Remote MCP · OAuth · 5 tools
Google Docs logo

Google Docs MCP Server: Secure AI Agent Access to Google Docs

Connect Claude, ChatGPT, and Cursor to Google Docs through PortEden's remote MCP server. OAuth, per-document controls, and a data firewall that controls every read and edit.

Connect to Claude

Free tier · No credit card required

What is the Google Docs MCP server?

The Google Docs MCP server lets AI agents read, edit, and search documents through the Model Context Protocol. Connect a client like Claude, ChatGPT, or Cursor to one remote endpoint at https://mcp.porteden.com/google-docs and the agent works with your Docs directly, with no copy and paste.

PortEden's server exposes tools to search, read, edit, rename, and delete Google Docs. What makes it different from a generic Google Docs MCP is the data firewall in front of those tools: PortEden inspects every tool-call request, applies your access policy, and redacts sensitive content in the response before the agent ever sees it.

The result is secure Google Docs access for AI agents. You decide whether a client can only read or can also edit, scope it to specific documents, redact sensitive passages, and review every call in an audit log. OAuth handles authentication, so there is no static key to leak.

Google Docs MCP tools

Every tool can be allowed or denied per client. Access levels are enforced at the firewall on each call.

These are the 5 tools documented today. PortEden's live Google Docs server is expanding, and newer tools will appear here as they are documented.

ToolAccessWhat it does
google_docs_searchreadSearch Google Docs across connected drives.
google_docs_readreadRead a Doc's content as plain text or structured paragraphs.
google_docs_editwriteEdit a Doc with insert, append, and replace operations.
google_docs_renamewriteRename a Doc.
google_docs_deletedeleteSend a Doc to trash.

Connect Google Docs to Claude, ChatGPT, Cursor, and more

Point any MCP-compatible client at the remote URL and sign in to PortEden once with OAuth.

# Claude Web or Desktop, then Settings, Connectors, Add custom connector
https://mcp.porteden.com/google-docs 
 
# Authenticate to PortEden once with OAuth. Claude can now call the
# Google Docs tools under the access policy you set.

Available on Claude Pro, Team, and Enterprise. The same flow works for Claude Cowork.

The security-first Google Docs MCP

PortEden is the data firewall for AI.

Granular access control

Decide exactly what each AI client can do with your documents. Keep an agent read-only, allow edits but never deletes, or scope a connection to specific documents, so an agent only touches what policy allows.

  • Read-only by default: deny google_docs_edit, google_docs_rename, and google_docs_delete for a research agent.
  • Edit but never delete: allow google_docs_edit while denying google_docs_delete.
  • Per-document scope: limit a client to a named set of Docs and block the rest.
Learn more about granular access control

Data redaction

PortEden runs a redaction pass on every tool response before it leaves the firewall. Sensitive passages are replaced with stable placeholders, so the agent can summarize or rewrite a document without the raw content entering the model's context.

  • Strip PII, PAN (card numbers), and secrets from document text before the agent sees them.
  • Mask names and contact details in a contract while keeping the structure readable.
  • Round-trip edits are de-redacted server-side, so an edit aimed at a placeholder lands on the right text.
Learn more about data redaction

Audit trail

Every Google Docs tool call is recorded: which client, which user, which tool, the arguments passed, the policy decision, and the redacted response. Export it or stream it to your SIEM for review.

  • See exactly which documents an agent read and which it edited, with timestamps.
  • Reconstruct any tool call: the request, the rule that fired, and the response returned.
  • Stream to Splunk, Datadog, or S3 for retention and review.
Learn more about audit trail

RBAC and policy groups

Bind each MCP connection to a user or role with a scoped, revocable token. Group policies by team so a new hire inherits the right document access on day one, and revocation is instant and server-side.

  • Issue per-user tokens scoped to the verbs and documents that role needs.
  • Apply one policy group across a team instead of editing rules client by client.
  • Revoke a token server-side the moment a contract ends, with no Google account round-trip.
Learn more about rbac and policy groups

Set up the secure Google Docs MCP in minutes

1

Add the connector

In your AI client, add a custom connector or HTTP MCP server pointing at https://mcp.porteden.com/google-docs.

2

Authenticate with OAuth

Sign in to PortEden once and connect your Google account. The client never holds your Google refresh token.

3

Set your Docs policy

Choose read-only or read-write, scope to specific documents, and turn on redaction for sensitive passages.

4

Verify in the audit log

Run a prompt, then watch the tool calls land in your PortEden audit log with the rule that fired on each one.

Works with every MCP client
Claude DesktopClaude WebChatGPTCursorWindsurfClineZed

Google Docs MCP FAQ

What is the Google Docs MCP server?
It is a remote MCP (Model Context Protocol) server that lets MCP-compatible AI clients like Claude, ChatGPT, and Cursor read, edit, and search Google Docs through a single hosted endpoint at https://mcp.porteden.com/google-docs. PortEden puts a data firewall in front of every tool so you control what the AI can see and do.
How do I connect Claude to Google Docs using MCP?
In Claude Web or Desktop, open Settings, then Connectors, then Add custom connector, and paste https://mcp.porteden.com/google-docs. Authenticate to PortEden once with OAuth and connect your Google account. Claude can then call the Docs tools. The same URL works in ChatGPT Connectors and in Cursor's MCP settings.
Is the Google Docs MCP server secure?
That is the whole point of PortEden. The connection uses OAuth, so there is no static key to leak. Every tool call passes through a policy decision, sensitive passages are redacted before the agent sees them, and every call is written to an audit log. You can keep a client read-only or scope it to specific documents.
Can I give an AI agent read-only access to Google Docs?
Yes. Deny google_docs_edit, google_docs_rename, and google_docs_delete in your policy and the agent keeps the read tools (google_docs_search and google_docs_read). You can also allow edits while denying deletes, or limit the agent to a named set of documents.
Does redaction stop the agent from editing a document?
No. PortEden replaces sensitive passages with stable placeholders rather than removing them, so the agent can summarize and rewrite by handle. Round-trip edits are de-redacted server-side, so an edit aimed at a placeholder lands on the right text. The raw values never enter the model's context.
What Google Docs tools does the MCP server expose?
The documented set is five tools: google_docs_search and google_docs_read for reading; google_docs_edit and google_docs_rename for changes; and google_docs_delete for removal. Each tool can be allowed or denied per client.
Which AI clients work with the Google Docs MCP server?
Any MCP-compatible client. That includes Claude Desktop, Claude Web, ChatGPT (via Connectors), Cursor, Windsurf, Cline, and Zed. Point the client at the remote URL and authenticate once.
Does it cost anything to use the Google Docs MCP server?
There is a free tier that covers 1,000 tool calls per month. Paid plans raise the limit. A tool call is one MCP request. See the pricing page for current limits.

Keep Exploring

Connect Google Docs to AI, without leaking the underlying data.

Five-minute setup over OAuth. The free tier covers 1,000 tool calls per month.

See pricing