Clear conversation history for a specific conversation ID
AI agents call clear_conversation to permanently remove resources in NanoBanana MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing conversation history is an irreversible deletion of data (the conversation history). Once cleared, the history cannot be recovered, making this a destructive operation. The blast radius is medium since it only affects conversation history within this specific MCP server, not broader system data.
From the tool's definition Clear conversation history for a specific conversation ID
Attacks that exploit this kind of access
Clear conversation history for a specific conversation ID. It is categorised as a Destructive tool in the NanoBanana MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the NanoBanana MCP server in PolicyLayer and add a rule for clear_conversation: 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 MCP. Nothing to install.
clear_conversation is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_conversation 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 clear_conversation. 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.
clear_conversation is provided by the NanoBanana MCP server (pistachiomatt/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 →