AI agents invoke run_scenario to trigger actions in SafeBreach MCP Server. 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.
The tool executes attack simulation scenarios on a live platform. While SafeBreach scenarios are security testing tools (legitimate use), execution of such scenarios without proper safeguards could trigger unintended security assessments, disrupt systems, or expose vulnerabilities.
From the tool's definition Tool name 'run_scenario' in context of SafeBreach's Breach and Attack Simulation platform; sibling tools include 'create_new_studio_attack' and 'get_full_simulation_logs', indicating this server manages attack simulations.
Documented attack patterns abuse exactly the kind of access run_scenario gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SafeBreach MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_scenario:
{
"version": "1",
"default": "deny",
"tools": {
"run_scenario": {
"limits": [
{
"counter": "run_scenario_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_scenario 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.
run_scenario. It is categorised as a Execute tool in the SafeBreach MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SafeBreach MCP Server MCP server in PolicyLayer and add a rule for run_scenario: 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 SafeBreach MCP Server. Nothing to install.
run_scenario 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_scenario 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_scenario. 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_scenario is provided by the SafeBreach MCP Server MCP server (safebreach/safebreach-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SafeBreach MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
35 SafeBreach MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.