AI agents use create_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.
create_permission modifies sharing settings on Google Drive files, allowing an AI agent to grant access to files to arbitrary users or groups. While the change is reversible (permissions can be removed), the high severity reflects the risk of unintended sharing of sensitive documents to external parties or broader audiences.
From the tool's definition Tool description states: 'Share a Google Drive file with a user, group, domain, or anyone.' This modifies file permissions, which is a reversible change to metadata/access control.
Attacks that exploit this kind of access
Share a Google Drive file with a user, group, domain, or anyone. 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 create_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.
create_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 create_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 create_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.
create_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 →