Resume an interrupted engagement from its last checkpoint. Returns immediately with status='running' and runs the resume in a background task — same async-task pattern as start_engagement (commit f2c58d3) so the MCP client doesn't time out on long resumes. Poll get_engagement_status / get_finding...
AI agents invoke resume_engagement to trigger actions in Pentest Ai. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Resuming a pentest engagement triggers real security tool execution (scans, exploitation attempts, PoC generation) in a background task. This is an Execute-category action because it restarts autonomous offensive security operations against target systems. The blast radius is high since it can trigger vulnerability exploitation, active scanning, and attack chain discovery against potentially live infrastructure.
From the tool's definition Resume an interrupted engagement from its last checkpoint... runs the resume in a background task
Documented attack patterns abuse exactly the kind of access resume_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 resume_engagement:
{
"version": "1",
"default": "deny",
"tools": {
"resume_engagement": {
"limits": [
{
"counter": "resume_engagement_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}resume_engagement stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Resume an interrupted engagement from its last checkpoint. Returns immediately with status='running' and runs the resume in a background task — same async-task pattern as start_engagement (commit f2c58d3) so the MCP client doesn't time out on long resumes. Poll get_engagement_status / get_findings to track progress. It is categorised as a Execute tool in the Pentest Ai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pentest Ai MCP server in PolicyLayer and add a rule for resume_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.
resume_engagement is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the resume_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 resume_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.
resume_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.