// SCAN REPORT

SafeBreach MCP Server

35 tools. 10 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 12 Jun 2026

10 can modify or destroy data

25 read-only

35 tools total

Community server · catalogue entry verified 12/06/2026

How to control SafeBreach MCP Server ↓

TOOL MAP

What SafeBreach MCP Server exposes to your agents

Read (25) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous SafeBreach MCP Server tools

Execute · High run_adhoc_scenario This tool executes external operations (attack simulations) whose effects depend on arguments (which scenario to run, what parameters). Execute · High run_scenario The tool executes attack simulation scenarios on a live platform. Execute · High run_studio_attack This tool executes a simulated attack within the SafeBreach platform. Write · High create_new_studio_attack The 'create' prefix strongly suggests this tool creates a new attack simulation in the SafeBreach Studio.

10 of SafeBreach MCP Server's 35 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control SafeBreach MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and SafeBreach MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "create_new_studio_attack": {
    "limits": [
      {
        "counter": "create_new_studio_attack_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_all_studio_attacks": {
    "limits": [
      {
        "counter": "get_all_studio_attacks_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register SafeBreach MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SAFEBREACH →

Free to start. No card required.

FULL CATALOGUE

All 35 SafeBreach MCP Server tools

EXECUTE 3 tools

Execute run_adhoc_scenario run_adhoc_scenario Execute run_scenario run_scenario Execute run_studio_attack run_studio_attack

WRITE 4 tools

Write create_new_studio_attack create_new_studio_attack Write save_studio_attack_draft save_studio_attack_draft Write set_studio_attack_status set_studio_attack_status Write update_studio_attack_draft update_studio_attack_draft

READ 25 tools

Read get_all_studio_attacks get_all_studio_attacks Read get_console_simulators get_console_simulators Read get_full_simulation_logs get_full_simulation_logs Read get_peer_benchmark_score get_peer_benchmark_score Read get_playbook_attack_details get_playbook_attack_details Read get_playbook_attacks get_playbook_attacks Read get_scenario_details get_scenario_details Read get_scenarios get_scenarios Read get_security_control_drifts get_security_control_drifts Read get_security_control_event_details get_security_control_event_details Read get_security_controls_events get_security_controls_events Read get_simulation_lineage get_simulation_lineage Read get_simulation_result_drifts get_simulation_result_drifts Read get_simulation_status_drifts get_simulation_status_drifts Read get_simulator_details get_simulator_details Read get_studio_attack_latest_result get_studio_attack_latest_result Read get_studio_attack_source get_studio_attack_source Read get_test_details get_test_details Read get_test_drifts get_test_drifts Read get_test_findings_counts get_test_findings_counts Read get_test_findings_details get_test_findings_details Read get_test_simulation_details get_test_simulation_details Read get_test_simulations get_test_simulations Read get_tests get_tests Read validate_studio_code validate_studio_code

OTHER 3 tools

Other convert_datetime_to_epoch convert_datetime_to_epoch Other convert_epoch_to_datetime convert_epoch_to_datetime Other manage_test manage_test

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about SafeBreach MCP Server

How do I prevent bulk modifications through SafeBreach MCP Server? +

The SafeBreach MCP Server server has 4 write tools including create_new_studio_attack, save_studio_attack_draft, set_studio_attack_status. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach SafeBreach MCP Server.

How many tools does the SafeBreach MCP Server MCP server expose? +

35 tools across 3 categories: Execute, Read, Write. 25 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on SafeBreach MCP Server? +

Register the SafeBreach MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every SafeBreach MCP Server tool call.

Deterministic rules across all 35 SafeBreach MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SAFEBREACH →

Free to start. No card required.

35 SafeBreach MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.