Search Drive files. Uses Drive query syntax.
AI agents call drive_search to retrieve information from Gworkspace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation on Google Drive files using the Drive query syntax. It retrieves information about files without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an AI agent could retrieve unauthorized file metadata or discover sensitive files, but cannot directly access their contents or alter them. This is a classic Read operation.
From the tool's definition Tool name is 'drive_search' and description states it 'Search[es] Drive files'. The action is purely retrieval/querying with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Search Drive files. Uses Drive query syntax. It is categorised as a Read tool in the Gworkspace MCP Server, which means it retrieves data without modifying state.
Register the Gworkspace 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 Gworkspace. 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 Gworkspace MCP server (leoonic/gworkspace-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 →