Start a reconnaissance scan against a target. Returns immediately with an engagement_id while the recon agent runs asynchronously. Poll get_engagement_status(engagement_id) for status and get_findings(engagement_id=...) for results. Depth levels: - passive: OSINT only, no direct interaction - sta...
AI agents invoke run_recon 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.
run_recon initiates active security scanning operations whose effects depend on the target and depth argument provided. While not destructive or financial, it executes external tools and commands (port scanning, vulnerability scanning) that produce observable effects on target systems and network interactions. The 'deep' option explicitly performs 'full active scanning' making this clearly an Execute category tool.
From the tool's definition Tool performs reconnaissance scanning with configurable depth levels including 'active scanning', 'port scans', and 'vuln scans' against targets. These are executable operations that interact with external systems and trigger security tools.
Documented attack patterns abuse exactly the kind of access run_recon 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 run_recon:
{
"version": "1",
"default": "deny",
"tools": {
"run_recon": {
"limits": [
{
"counter": "run_recon_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_recon 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.
Start a reconnaissance scan against a target. Returns immediately with an engagement_id while the recon agent runs asynchronously. Poll get_engagement_status(engagement_id) for status and get_findings(engagement_id=...) for results. Depth levels: - passive: OSINT only, no direct interaction - standard: Passive + light active scanning - deep: Full active scanning including port scans, vuln scans. 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 run_recon: 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.
run_recon 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 run_recon 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 run_recon. 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.
run_recon 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.