Scan codebase and build dependency graph mapping design token usage across files. This is the foundation for impact analysis.
AI agents call build_dependency_graph to retrieve information from Sunnyside Figma MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool scans the codebase and builds a dependency graph — it reads and analyzes files to map token usage. No data is modified, deleted, or executed. The severity is medium because it reads potentially sensitive codebase structure and design system internals across many files, giving broad visibility into the project architecture.
From the tool's definition Scan codebase and build dependency graph mapping design token usage across files
Documented attack patterns abuse exactly the kind of access build_dependency_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sunnyside Figma MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for build_dependency_graph:
{
"version": "1",
"default": "deny",
"tools": {
"build_dependency_graph": {}
}
}build_dependency_graph 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.
Scan codebase and build dependency graph mapping design token usage across files. This is the foundation for impact analysis. It is categorised as a Read tool in the Sunnyside Figma MCP MCP Server, which means it retrieves data without modifying state.
Register the Sunnyside Figma MCP server in PolicyLayer and add a rule for build_dependency_graph: 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 Sunnyside Figma MCP. Nothing to install.
build_dependency_graph 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 build_dependency_graph 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 build_dependency_graph. 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.
build_dependency_graph is provided by the Sunnyside Figma MCP server (tercumantanumut/sunnysidefigma-context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 31 Sunnyside Figma MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
31 Sunnyside Figma MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.