AI agents call similarity-figma to retrieve information from Feuse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches Figma design data and performs visual comparison analysis without modifying, executing code, deleting data, or affecting financial systems. It retrieves and analyzes existing design assets and generated code outputs for validation purposes, making it a Read category tool with low severity.
From the tool's definition Tool description indicates it 'retrieves Figma prototypes' and performs 'similarity comparison' between prototype screenshots and generated code screenshots. The verbs are 'get' and 'compare', which are read-only operations.
Documented attack patterns abuse exactly the kind of access similarity-figma gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Feuse, and nothing reaches the server without passing your rules. This is the rule we recommend for similarity-figma:
{
"version": "1",
"default": "deny",
"tools": {
"similarity-figma": {}
}
}similarity-figma 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.
获取Figma原型图，请你结合项目源码并通过原型图与生成的代码页面的截图进行相似性比对. It is categorised as a Read tool in the Feuse MCP Server, which means it retrieves data without modifying state.
Register the Feuse MCP server in PolicyLayer and add a rule for similarity-figma: 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 Feuse. Nothing to install.
similarity-figma 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 similarity-figma 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 similarity-figma. 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.
similarity-figma is provided by the Feuse MCP server (panzer-jack/feuse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Feuse tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Feuse tools catalogued and risk-classified — across an index of 42,500+ MCP servers.