Continue editing the LAST image that was generated or edited in this session, optionally using additional reference images. Use this for iterative improvements, modifications, or changes to the most recent image. This automatically uses the previous image without needing a file path.
AI agents use continue_editing to create or update resources in Nano Banana — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nano Banana environment.
This tool modifies/creates image data by editing the most recent image in the session. It produces a new or updated image, which is a reversible write operation (the original image data is implicitly preserved in session history and can be reverted). No code execution, deletion, or financial transaction is involved.
From the tool's definition Continue editing the LAST image that was generated or edited in this session, optionally using additional reference images. Use this for iterative improvements, modifications, or changes to the most recent image.
Attacks that exploit this kind of access
Continue editing the LAST image that was generated or edited in this session, optionally using additional reference images. Use this for iterative improvements, modifications, or changes to the most recent image. This automatically uses the previous image without needing a file path. It is categorised as a Write tool in the Nano Banana MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nano Banana MCP server in PolicyLayer and add a rule for continue_editing: 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.
continue_editing is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the continue_editing 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 continue_editing. 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.
continue_editing 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 →