AI agents call docs_get_document_summary to retrieve information from Google without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and returns document metadata (title, ID, revision, created time) without creating, modifying, deleting, or executing any operations. It is a passive query operation with no side effects, fitting squarely in the Read category. Severity is low because metadata retrieval poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'docs_get_document_summary' and description 'Get summary metadata of a Google Doc (title, ID, revision, created time)' indicate retrieval of read-only metadata with no modification or side effects.
Attacks that exploit this kind of access
Get summary metadata of a Google Doc (title, ID, revision, created time). It is categorised as a Read tool in the Google MCP Server, which means it retrieves data without modifying state.
Register the Google MCP server in PolicyLayer and add a rule for docs_get_document_summary: 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. Nothing to install.
docs_get_document_summary 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 docs_get_document_summary 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 docs_get_document_summary. 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.
docs_get_document_summary is provided by the Google MCP server (psckeithw/mcp-google). 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 →