scaffold_nodebench_project
Create a complete project template pre-configured for nodebench-mcp. Generates: package.json, AGENTS.md, .mcp.json, .parallel-agents/, .github/workflows/, tsconfig.json, .gitignore, README.md, and src/ directory. Everything an agent needs to start working immediately with the full AI Flywheel met...
This record as markdown: /tools/io-github-homenshum-nodebench/scaffold-nodebench-project.md
What scaffold_nodebench_project does on Nodebench
AI agents use scaffold_nodebench_project 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_nodebench_project is rated Medium
This tool creates multiple files and directories in the filesystem. It is a Write operation (file/project scaffolding). While it generates many files, these are reversible (files can be deleted). The dryRun=true default slightly mitigates risk, but misuse could overwrite existing project files. Severity is medium due to potential to overwrite existing configurations.
From the tool's definition Create a complete project template...Generates: package.json, AGENTS.md, .mcp.json, .parallel-agents/, .github/workflows/, tsconfig.json, .gitignore, README.md, and src/ directory
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs scaffold_nodebench_project 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_nodebench_project, this is the rule to start with:
scaffold_nodebench_project 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_nodebench_project call is checked against it from then on.
Questions about scaffold_nodebench_project
Create a complete project template pre-configured for nodebench-mcp. Generates: package.json, AGENTS.md, .mcp.json, .parallel-agents/, .github/workflows/, tsconfig.json, .gitignore, README.md, and src/ directory. Everything an agent needs to start working immediately with the full AI Flywheel methodology. Use dryRun=true (default) to preview what will be created. 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_nodebench_project: 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_nodebench_project 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_nodebench_project 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_nodebench_project. 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_nodebench_project 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