scaffold_directory
Scaffold directory structure following OpenClaw patterns. Creates organized subdirectories and placeholder files for: agent_loop, telemetry, evaluation, verification, multi_channel, self_learning, governance.
This record as markdown: /tools/io-github-homenshum-nodebench/scaffold-directory.md
What scaffold_directory does on Nodebench
AI agents use scaffold_directory to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.
Why scaffold_directory is rated Medium
This tool creates new directories and placeholder files on the filesystem. It is a Write operation (reversible creation of files/directories) rather than Destructive since it creates new content rather than deleting existing data. Severity is medium because an AI agent misusing it could create unwanted directory structures and files across the filesystem, though it does not delete or overwrite existing data.
From the tool's definition Scaffold directory structure... Creates organized subdirectories and placeholder files
Attacks that exploit this kind of access
The rule that runs scaffold_directory safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For scaffold_directory, this is the rule to start with:
scaffold_directory stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every scaffold_directory call is checked against it from then on.
Questions about scaffold_directory
Scaffold directory structure following OpenClaw patterns. Creates organized subdirectories and placeholder files for: agent_loop, telemetry, evaluation, verification, multi_channel, self_learning, governance. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nodebench MCP server in PolicyLayer and add a rule for scaffold_directory: 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 Nodebench. Nothing to install.
scaffold_directory 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_directory 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_directory. 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_directory is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue