edit_doc · Google MCP: Risk & Policy

WHAT IT DOES

What edit_doc does on Google

AI agents use edit_doc to create or update resources in Google — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google environment.

WHY IT NEEDS A POLICY

Why edit_doc needs a policy

edit_doc modifies document content in-place through insert, replace, and append operations, which are characteristic Write operations. While it includes 'delete', the context (find/replace, append, insert) indicates targeted content removal within a doc rather than irreversible destruction of the document itself. The document and its history remain intact.

From the tool's definition Tool description states it "Supports insert, delete, replace (find/replace all), and append" on Google Docs. These are all reversible modifications.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

edit_doc Rate-limited

edit_doc stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "edit_doc": {
      "limits": [
        {
          "counter": "edit_doc_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Google, so you can run agents against it safely.

FAQ

Questions about edit_doc

What does the edit_doc tool do? +

Edit a Google Doc in-place. Supports insert, delete, replace (find/replace all), and append. It is categorised as a Write tool in the Google MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on edit_doc? +

Register the Google MCP server in PolicyLayer and add a rule for edit_doc: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Google. Nothing to install.

What risk level is edit_doc? +

edit_doc is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit edit_doc? +

Yes. Add a rate_limit block to the edit_doc rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block edit_doc completely? +

Set action: deny in the PolicyLayer policy for edit_doc. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides edit_doc? +

edit_doc is provided by the Google MCP server (ztgluis/google-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

edit_doc is one line of Google's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →