get_doc
AI agents call get_doc to retrieve information from Mcp Google Agent Platform Docs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves documentation content with no side effects. It reads from a static documentation corpus without creating, modifying, deleting, or executing any operations. The empty description is somewhat limiting, but the context of a documentation server and the naming pattern strongly indicate a read-only retrieval function.
From the tool's definition Tool name 'get_doc' combined with sibling tools 'list_models', 'list_sections', and 'search_docs' indicates a documentation retrieval system. The server purpose is to provide 'searchable' access to 'Google Agent Platform Docs.'
Attacks that exploit this kind of access
get_doc. It is categorised as a Read tool in the Mcp Google Agent Platform Docs MCP Server, which means it retrieves data without modifying state.
Register the Mcp Google Agent Platform Docs MCP server in PolicyLayer and add a rule for get_doc: 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 Agent Platform Docs. Nothing to install.
get_doc 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 get_doc 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 get_doc. 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.
get_doc is provided by the Mcp Google Agent Platform Docs MCP server (opengerwin/mcp-google-agent-platform-docs). 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 →