Search for files in Google Drive
AI agents call gdrive_search to retrieve information from Mcp Gdrive without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data (file metadata and locations) from Google Drive without creating, modifying, or deleting any resources. It has no side effects beyond returning search results. It is a standard read operation, warranting 'Read' category and low severity since misuse would only expose information the agent already has access to.
From the tool's definition Tool name is 'gdrive_search' and description states it 'Search for files in Google Drive' — a query operation with no modification or execution of external processes.
Attacks that exploit this kind of access
Search for files in Google Drive. It is categorised as a Read tool in the Mcp Gdrive MCP Server, which means it retrieves data without modifying state.
Register the Mcp Gdrive MCP server in PolicyLayer and add a rule for gdrive_search: 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 Mcp Gdrive. Nothing to install.
gdrive_search 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 gdrive_search 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 gdrive_search. 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.
gdrive_search is provided by the Mcp Gdrive MCP server (@isaacphi/mcp-gdrive). 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 →