This record as markdown: /tools/io-github-homenshum-nodebench/getplan.md
What getPlan does on Nodebench
AI agents call getPlan to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why getPlan is rated Low
This tool retrieves data (a task plan) by identifier without modifying, deleting, or executing anything. It is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'getPlan' and description 'Retrieve a task plan by ID' indicate a query/fetch operation with no side effects.
Attacks that exploit this kind of access
The rule that runs getPlan 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 getPlan, this is the rule to start with:
getPlan is read-only, so it stays allowed. 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 getPlan call is checked against it from then on.
Questions about getPlan
Retrieve a task plan by ID. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for getPlan: 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.
getPlan is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the getPlan 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 getPlan. 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.
getPlan 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