List all shared drives
AI agents call list_shared_drives to retrieve information from Mcp Google Drive without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about shared drives without creating, modifying, deleting, or executing any operations. It is a pure read operation with minimal risk; the worst-case misuse would be enumeration of available shared drives, which is informational only.
From the tool's definition Tool name is 'list_shared_drives' and description states 'List all shared drives' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all shared drives. It is categorised as a Read tool in the Mcp Google Drive MCP Server, which means it retrieves data without modifying state.
Register the Mcp Google Drive MCP server in PolicyLayer and add a rule for list_shared_drives: 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 Google Drive. Nothing to install.
list_shared_drives 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 list_shared_drives 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 list_shared_drives. 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.
list_shared_drives is provided by the Mcp Google Drive MCP server (longtran2404/mcp-google-drive). 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 →