AI agents call get_file_metadata to retrieve information from Google without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information about a file's properties without altering data, executing code, or triggering external operations. It is a read-only operation with minimal blast radius—the worst outcome of misuse would be exposure of file metadata already accessible to the authenticated user.
From the tool's definition Tool name is 'get_file_metadata' and description states it retrieves metadata (name, type, size, owner, dates, parents, etc.) with no modification or execution capability indicated.
Attacks that exploit this kind of access
Get metadata for a Google Drive file (name, type, size, owner, dates, parents, etc.). It is categorised as a Read tool in the Google MCP Server, which means it retrieves data without modifying state.
Register the Google MCP server in PolicyLayer and add a rule for get_file_metadata: 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.
get_file_metadata is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_file_metadata 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 get_file_metadata. 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.
get_file_metadata 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 →