Preview a scenario before deployment with detailed information. IMPORTANT: Generates a FRESH configuration preview for the specified scenario. Use this BEFORE deploy_scenario to verify what will be deployed. Shows VMs, network topology, resource requirements, and deployment estimates. Each previe...
AI agents call preview_scenario to retrieve information from Ludus FastMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
preview_scenario retrieves and displays information about a scenario configuration without making any changes to the system. It generates a preview (read operation) to help users understand what would be deployed, but does not actually deploy, create, modify, or delete any resources.
From the tool's definition Tool description states it 'Preview a scenario before deployment' and 'Shows VMs, network topology, resource requirements, and deployment estimates.' The word 'Preview' and 'Shows' indicate read-only retrieval of configuration information.
Documented attack patterns abuse exactly the kind of access preview_scenario gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ludus FastMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for preview_scenario:
{
"version": "1",
"default": "deny",
"tools": {
"preview_scenario": {}
}
}preview_scenario 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.
Preview a scenario before deployment with detailed information. IMPORTANT: Generates a FRESH configuration preview for the specified scenario. Use this BEFORE deploy_scenario to verify what will be deployed. Shows VMs, network topology, resource requirements, and deployment estimates. Each preview call builds the scenario from scratch with your specified parameters. Args: scenario_key: Scenario identifier (e.g., 'redteam-lab-lite') siem_type: SIEM type to include (wazuh, splunk, elastic, security-onion, none) resource_profile: Resource allocation profile (minimal, recommended, maximum) Returns: Preview with configuration, visualization, and estimates including: - Complete VM list with hostnames, templates, resources - Network rules and VLAN topology - Resource summary (total RAM, CPUs, disk space) - Estimated deployment time - Exact deployment command to use Recommended workflow: 1. preview_scenario('redteam-lab-lite', 'none', 'minimal') 2. Review the VM list and resources 3. deploy_scenario('redteam-lab-lite', 'none', 'minimal'). It is categorised as a Read tool in the Ludus FastMCP MCP Server, which means it retrieves data without modifying state.
Register the Ludus Fast MCP server in PolicyLayer and add a rule for preview_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 Ludus FastMCP. Nothing to install.
preview_scenario 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 preview_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 preview_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.
preview_scenario is provided by the Ludus Fast MCP server (tjnull/ludus-fastmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 201 Ludus FastMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
201 Ludus FastMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.