Search files in Google Drive
AI agents call drive_search to retrieve information from Google Drive MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search functionality is a read-only operation that queries and returns file information from Google Drive. It has no side effects, does not execute code, does not modify data, and does not delete or move files. The blast radius of misuse is minimal—an attacker could discover files they shouldn't see, but cannot act on them through this tool alone. This is appropriately classified as a Read risk.
From the tool's definition Tool name 'drive_search' and description 'Search files in Google Drive' indicate a query operation that retrieves file metadata without modifying, executing, or deleting data.
Attacks that exploit this kind of access
Search files in Google Drive. It is categorised as a Read tool in the Google Drive MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Drive MCP Server MCP server in PolicyLayer and add a rule for drive_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 Google Drive MCP Server. Nothing to install.
drive_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 drive_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 drive_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.
drive_search is provided by the Google Drive MCP Server MCP server (rishipradeep-think41/google-drive-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 →