AI agents use scaffold_producer 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 creates new files/code (API stubs) based on analysis of existing client code. It is a code generation/write operation — it produces new artifacts on disk but does not execute them, delete anything, or involve financial operations. Misuse could generate incorrect stubs that propagate schema mismatches, hence medium severity.
From the tool's definition Generate API stubs from client usage patterns. Infers schema from how client code calls the API.
Attacks that exploit this kind of access
Generate API stubs from client usage patterns. Infers schema from how client code calls the API. 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_producer: 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_producer 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_producer 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_producer. 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_producer 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 →