AI agents use close_engagement to create or update resources in Pentest Ai — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pentest Ai environment.
This tool updates engagement metadata by marking a record as completed. It is Write rather than Destructive because closure/marking complete is typically reversible (engagement can usually be reopened or re-opened).
From the tool's definition 'Close an engagement and mark it as completed' - modifies state of an engagement record, changing its status from active to completed. This is a reversible state change operation.
Documented attack patterns abuse exactly the kind of access close_engagement gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pentest Ai, and nothing reaches the server without passing your rules. This is the rule we recommend for close_engagement:
{
"version": "1",
"default": "deny",
"tools": {
"close_engagement": {
"limits": [
{
"counter": "close_engagement_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}close_engagement stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Close an engagement and mark it as completed. It is categorised as a Write tool in the Pentest Ai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pentest Ai MCP server in PolicyLayer and add a rule for close_engagement: 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 Pentest Ai. Nothing to install.
close_engagement 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 close_engagement 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 close_engagement. 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.
close_engagement is provided by the Pentest Ai MCP server (0xsteph/pentest-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 51 Pentest Ai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
51 Pentest Ai tools catalogued and risk-classified — across an index of 42,500+ MCP servers.