List every registered web probe with its metadata. Use this to discover what bug classes ptai can test for. The LLM driving an engagement picks probes by name and calls run_probe. Filters: - bug_class: only return probes for this bug class (e.g. sqli, idor, ssti, race_condition). - requires_auth_...
AI agents call list_probes to retrieve information from Pentest Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only discovery of available probes and their metadata. It returns information to inform which probes to invoke later via run_probe, with no side effects, data modification, or execution of security tests. The description emphasizes it helps the LLM "discover what bug classes ptai can test for" — a pure query operation.
From the tool's definition list_probes retrieves and queries metadata about registered web probes with optional filters; explicitly documented as "List every registered web probe with its metadata" with filtering options for bug_class and requires_auth_only.
Documented attack patterns abuse exactly the kind of access list_probes 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 list_probes:
{
"version": "1",
"default": "deny",
"tools": {
"list_probes": {}
}
}list_probes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List every registered web probe with its metadata. Use this to discover what bug classes ptai can test for. The LLM driving an engagement picks probes by name and calls run_probe. Filters: - bug_class: only return probes for this bug class (e.g. sqli, idor, ssti, race_condition). - requires_auth_only: only return probes that need a logged-in session (call set_engagement_auth first or pass auth_profile to run_probe). It is categorised as a Read tool in the Pentest Ai MCP Server, which means it retrieves data without modifying state.
Register the Pentest Ai MCP server in PolicyLayer and add a rule for list_probes: 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.
list_probes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_probes 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 list_probes. 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.
list_probes 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.