AI agents use update_permission 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.
This tool modifies (rather than deletes) existing permissions on Drive files, which is a reversible write operation. However, it affects access control—a sensitive dimension. The severity is high because misconfigured permissions could expose files to unintended users or restrict legitimate access, and the blast radius scales with file sensitivity.
From the tool's definition Tool name 'update_permission' and description 'Update a permission role on a Google Drive file' indicate modification of access control settings on shared resources.
Attacks that exploit this kind of access
Update a permission role on a Google Drive file. 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.
Register the Google MCP server in PolicyLayer and add a rule for update_permission: 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.
update_permission is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_permission 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.
Set action: deny in the PolicyLayer policy for update_permission. 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.
update_permission 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →