Search Google Drive files.
AI agents call search_drive to retrieve information from Google Connections 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 files stored in Google Drive. It performs a search operation that returns results without creating, modifying, deleting, or executing anything. The search operation is non-destructive and has no side effects beyond returning matching file metadata or references.
From the tool's definition Tool name is 'search_drive' and description states 'Search Google Drive files.' The verb 'search' and the absence of any modification, deletion, or execution language indicates retrieval-only functionality with no side effects.
Attacks that exploit this kind of access
Search Google Drive files. It is categorised as a Read tool in the Google Connections MCP Server, which means it retrieves data without modifying state.
Register the Google Connections MCP server in PolicyLayer and add a rule for search_drive: 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 Connections. Nothing to install.
search_drive 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 search_drive 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 search_drive. 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.
search_drive is provided by the Google Connections MCP server (michaelzrork/google-connections-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 →