Coming soon — not yet implemented; the server returns a not-implemented notice (use the OverlayQA browser extension for visual comparison today). Will compare a live URL against a Figma frame and return visual differences and a match score.
AI agents call compare_visual to retrieve information from OverlayQA MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs comparative analysis and returns data (visual differences and a match score) without modifying any data or triggering external operations. It is purely informational/analytical in nature. The fact that it is not yet implemented further reduces any risk. Classification as Read is appropriate.
From the tool's definition Tool description states it will "compare a live URL against a Figma frame and return visual differences and a match score" — a retrieval and analysis operation with no side effects. The tool is explicitly marked as "Coming soon — not yet implemented."
Attacks that exploit this kind of access
Coming soon — not yet implemented; the server returns a not-implemented notice (use the OverlayQA browser extension for visual comparison today). Will compare a live URL against a Figma frame and return visual differences and a match score. It is categorised as a Read tool in the OverlayQA MCP MCP Server, which means it retrieves data without modifying state.
Register the OverlayQA MCP server in PolicyLayer and add a rule for compare_visual: 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 OverlayQA MCP. Nothing to install.
compare_visual 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 compare_visual 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 compare_visual. 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.
compare_visual is provided by the OverlayQA MCP server (overlayqa/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 →