Check if Gemini API token is configured
AI agents call get_configuration_status to retrieve information from Nano Banana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns configuration state. It has no side effects, does not trigger external operations, and does not modify any data. It is a simple status check, making it a Read category tool with low severity since misuse would only expose whether a token is configured, not enable harmful operations on its own.
From the tool's definition Tool is named 'get_configuration_status' with description 'Check if Gemini API token is configured' — this is a pure query operation that retrieves status information without modifying, executing, or affecting any external systems.
Attacks that exploit this kind of access
Check if Gemini API token is configured. It is categorised as a Read tool in the Nano Banana MCP Server, which means it retrieves data without modifying state.
Register the Nano Banana MCP server in PolicyLayer and add a rule for get_configuration_status: 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 Nano Banana. Nothing to install.
get_configuration_status 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_configuration_status 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_configuration_status. 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_configuration_status is provided by the Nano Banana MCP server (nano-banana-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 →