Converts Figma prototype transitions into deterministic navigation test cases and reports dead ends, unreachable screens, and basic flow coverage.
AI agents call flow_to_test_cases to retrieve information from Figma Spec without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though flow_to_test_cases only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Converts Figma prototype transitions into deterministic navigation test cases and reports dead ends, unreachable screens, and basic flow coverage. It is categorised as a Read tool in the Figma Spec MCP Server, which means it retrieves data without modifying state.
Register the Figma Spec MCP server in PolicyLayer and add a rule for flow_to_test_cases: 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 Figma Spec. Nothing to install.
flow_to_test_cases 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 flow_to_test_cases 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 flow_to_test_cases. 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.
flow_to_test_cases is provided by the Figma Spec MCP server (zaferdace/figma-spec-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.