createPlan
Create an explicit task plan as a markdown document with steps marked as pending/in_progress/completed
This record as markdown: /tools/io-github-homenshum-nodebench/createplan.md
What createPlan does on Nodebench
AI agents use createPlan 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 createPlan is rated Medium
The tool creates a new document artifact (markdown plan) with task steps, constituting data creation. This is reversible (plans can be edited or deleted), so it falls under Write rather than Destructive. The blast radius is medium since a malicious agent could create misleading or resource-intensive plans that waste time or misdirect activity, but the effect is not inherently irreversible or destructive.
From the tool's definition Tool name and description indicate it 'Create[s] an explicit task plan as a markdown document' with status tracking, which creates or modifies structured data (a plan document) reversibly.
Attacks that exploit this kind of access
The rule that runs createPlan 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 createPlan, this is the rule to start with:
createPlan 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 createPlan call is checked against it from then on.
Questions about createPlan
Create an explicit task plan as a markdown document with steps marked as pending/in_progress/completed. 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 createPlan: 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.
createPlan 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 createPlan 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 createPlan. 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.
createPlan 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