AI forensic verdict by Marcus Aurelius (Claude Sonnet 4).
AI agents call marcus_quick to retrieve information from Rug Munch Intelligence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing risk intelligence data to produce a verdict. It generates insights but does not execute trades, create accounts, modify data, or trigger external operations. While it provides security-critical information that could influence financial decisions, the tool itself is non-destructive and read-only.
From the tool's definition Tool name 'marcus_quick' with description 'AI forensic verdict' indicates an analytical, read-only tool that evaluates token risk data. The verb is passive analysis ('forensic verdict'), not creation, modification, execution of transactions, or deletion.
Attacks that exploit this kind of access
AI forensic verdict by Marcus Aurelius (Claude Sonnet 4). It is categorised as a Read tool in the Rug Munch Intelligence MCP Server, which means it retrieves data without modifying state.
Register the Rug Munch Intelligence MCP server in PolicyLayer and add a rule for marcus_quick: 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 Rug Munch Intelligence. Nothing to install.
marcus_quick 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 marcus_quick 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 marcus_quick. 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.
marcus_quick is provided by the Rug Munch Intelligence MCP server (marcus-rug-intel/rug-munch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →