Manually create a new ZAP session with unique timestamp
AI agents use create_new_session to create or update resources in ZAP MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ZAP MCP Server environment.
This tool creates new session objects, which is a Write operation (reversible data creation). It is not Read (no retrieval), not Destructive (sessions can be deleted), not Execute in the direct sense (it doesn't run external commands, though it may indirectly enable them), and not Financial.
From the tool's definition Tool description states it will 'create a new ZAP session with unique timestamp' - this is a creation operation that modifies ZAP's session state.
Attacks that exploit this kind of access
Manually create a new ZAP session with unique timestamp. It is categorised as a Write tool in the ZAP MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ZAP MCP Server MCP server in PolicyLayer and add a rule for create_new_session: 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 ZAP MCP Server. Nothing to install.
create_new_session 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 create_new_session 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 create_new_session. 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.
create_new_session is provided by the ZAP MCP Server MCP server (lisberndt/zap-mcp-server). 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 →