AI agents invoke run_studio_attack 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.
This tool executes a simulated attack within the SafeBreach platform. While the description is empty (lowering confidence slightly), the name 'run_studio_attack' and the context of a Breach and Attack Simulation platform make it clear this triggers execution of security testing operations. The effects depend on the attack configuration provided as arguments.
From the tool's definition Tool name 'run_studio_attack' combined with sibling tools like 'create_new_studio_attack' and 'get_full_simulation_logs' indicates this triggers execution of attack simulations.
Documented attack patterns abuse exactly the kind of access run_studio_attack 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_studio_attack:
{
"version": "1",
"default": "deny",
"tools": {
"run_studio_attack": {
"limits": [
{
"counter": "run_studio_attack_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_studio_attack 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_studio_attack. 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_studio_attack: 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_studio_attack 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_studio_attack 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_studio_attack. 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_studio_attack 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.