Generate interactive architecture heatmap visualization with D3.js. Shows files as nodes colored by score (green=good, red=critical), dependencies as links, violations highlighted. Click nodes to see details.
AI agents call visualize_architecture to retrieve information from MMI Architecture Analyzer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and visualizes existing architecture analysis data using D3.js visualization. It presents information through interactive display (node clicking, heatmap coloring) but performs no modifications, deletions, code execution, or side effects beyond rendering. This is fundamentally a data retrieval and presentation operation, placing it in the Read category with low risk.
From the tool's definition The tool generates and displays visualizations of architecture data. The description indicates it 'shows files as nodes' and 'click nodes to see details' - these are read-only presentation operations.
Attacks that exploit this kind of access
Generate interactive architecture heatmap visualization with D3.js. Shows files as nodes colored by score (green=good, red=critical), dependencies as links, violations highlighted. Click nodes to see details. It is categorised as a Read tool in the MMI Architecture Analyzer MCP Server, which means it retrieves data without modifying state.
Register the MMI Architecture Analyzer MCP server in PolicyLayer and add a rule for visualize_architecture: 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 MMI Architecture Analyzer. Nothing to install.
visualize_architecture 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 visualize_architecture 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 visualize_architecture. 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.
visualize_architecture is provided by the MMI Architecture Analyzer MCP server (lady-logic/mmi-analyzer). 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 →