AI agents use scaffold_consumer to create or update resources in Trace MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trace MCP environment.
This tool generates and creates new code files (TypeScript functions, React hooks, Zustand actions) from API schemas. It writes new files to the filesystem but is reversible (generated files can be deleted), placing it in the Write category. Misuse could overwrite existing code or generate incorrect client code leading to integration issues, warranting medium severity.
From the tool's definition Generate type-safe client code... Creates TypeScript functions, React hooks, or Zustand actions
Attacks that exploit this kind of access
Generate type-safe client code from API schemas. Creates TypeScript functions, React hooks, or Zustand actions with full type inference. It is categorised as a Write tool in the Trace MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Trace MCP server in PolicyLayer and add a rule for scaffold_consumer: 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 Trace MCP. Nothing to install.
scaffold_consumer is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scaffold_consumer 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 scaffold_consumer. 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.
scaffold_consumer is provided by the Trace MCP server (mnehmos/mnehmos.trace.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 →