AI agents call search_presentations to retrieve information from Gg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data (presentations) from Google Drive without creating, modifying, deleting, or executing any operations. It is a read-only search/list operation with no side effects, fitting squarely into the Read category. The blast radius is minimal as it only exposes existing data the user already has access to.
From the tool's definition Tool performs a search operation on Google Slides presentations in Drive. Description indicates it 'Search for' and 'lists recent presentations' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search for Google Slides presentations in Drive. Empty query lists recent presentations. It is categorised as a Read tool in the Gg MCP Server, which means it retrieves data without modifying state.
Register the Gg MCP server in PolicyLayer and add a rule for search_presentations: 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 Gg. Nothing to install.
search_presentations 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_presentations 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_presentations. 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_presentations is provided by the Gg MCP server (tannht/google-cloud-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 →