Shortcut tool to explicitly retrieve the canonical
AI agents call get_current_model to retrieve information from Gemini Docs MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information (the current model) without modifying data, executing code, or causing side effects. It is a simple read/query operation consistent with the server's documentation retrieval purpose. The incomplete description ('retrieve the canonical') limits confidence slightly, but the intent to fetch rather than modify is clear.
From the tool's definition Tool name 'get_current_model' and description indicating it 'retrieve[s]' data with no modification or destructive capabilities. Server context indicates documentation retrieval functions.
Attacks that exploit this kind of access
Shortcut tool to explicitly retrieve the canonical. It is categorised as a Read tool in the Gemini Docs MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Gemini Docs MCP Server MCP server in PolicyLayer and add a rule for get_current_model: 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 Gemini Docs MCP Server. Nothing to install.
get_current_model 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_current_model 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_current_model. 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_current_model is provided by the Gemini Docs MCP Server MCP server (philschmid/gemini-api-docs-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 →