AI agents use scaffold_feature to create or update resources in Codecks — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codecks environment.
This tool creates structured card hierarchies within the Codecks project management system. Creating cards is a Write operation—it modifies project state reversibly and can be undone (supported by the presence of 'archive_card' and 'delete_card' on the same server).
From the tool's definition Tool name 'scaffold_feature' combined with description 'Create a Hero card with Code/Design/Art/Audio sub-cards' indicates creation of multiple project management artifacts.
Attacks that exploit this kind of access
Create a Hero card with Code/Design/Art/Audio sub-cards. It is categorised as a Write tool in the Codecks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codecks MCP server in PolicyLayer and add a rule for scaffold_feature: 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 Codecks. Nothing to install.
scaffold_feature 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_feature 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_feature. 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_feature is provided by the Codecks MCP server (rangogamedev/codecks-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 →