AI agents call imugi_compare to retrieve information from Imugi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
imugi_compare performs a comparison operation that retrieves and analyzes visual data without creating, modifying, or deleting persistent state. It is purely observational—comparing two images and producing metrics. No code execution, financial transactions, or destructive actions are possible. This is a read-only analysis tool with minimal blast radius if misused by an AI agent.
From the tool's definition Tool returns SSIM score, pixel diff, and heatmap from comparing images—no modification, deletion, or execution of external operations. The description explicitly states it 'Returns' analysis data without side effects.
Attacks that exploit this kind of access
Compare a design image against a rendered screenshot. Returns SSIM score, pixel diff, and heatmap. For the full iterative workflow, prefer imugi_iterate which combines capture + compare + analyze. It is categorised as a Read tool in the Imugi MCP Server, which means it retrieves data without modifying state.
Register the Imugi MCP server in PolicyLayer and add a rule for imugi_compare: 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 Imugi. Nothing to install.
imugi_compare 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 imugi_compare 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 imugi_compare. 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.
imugi_compare is provided by the Imugi MCP server (m00n7682/imugi). 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 →