Get the list of generated/edited images in a session for reference
AI agents call get_image_history to retrieve information from Nanobanana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical image data from a session without modifying, deleting, or executing operations. It is purely informational—a query operation that lists previously generated or edited images. This poses minimal risk as it only exposes read access to existing session data.
From the tool's definition Tool name 'get_image_history' and description 'Get the list of generated/edited images in a session for reference' indicate retrieval-only functionality with no side effects.
Attacks that exploit this kind of access
Get the list of generated/edited images in a session for reference. It is categorised as a Read tool in the Nanobanana MCP Server, which means it retrieves data without modifying state.
Register the Nanobanana MCP server in PolicyLayer and add a rule for get_image_history: 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 Nanobanana. Nothing to install.
get_image_history 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_image_history 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_image_history. 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_image_history is provided by the Nanobanana MCP server (@ycse/nanobanana-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 →