AI agents use create_instance to create or update resources in Ns Hpc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ns Hpc environment.
This tool creates a new resource (sandbox instance with workspace directory). It is a reversible write operation — instances can presumably be deleted/archived later. No code execution is triggered by the creation itself, and there's no financial or destructive aspect. Medium severity because spawning sandbox environments could consume cluster resources or be a stepping stone to further exploitation.
From the tool's definition Create a new sandbox instance with a persistent workspace directory
Attacks that exploit this kind of access
Create a new sandbox instance with a persistent workspace directory. It is categorised as a Write tool in the Ns Hpc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ns Hpc MCP server in PolicyLayer and add a rule for create_instance: 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 Ns Hpc. Nothing to install.
create_instance 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 create_instance 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 create_instance. 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.
create_instance is provided by the Ns Hpc MCP server (li-yq/namespaced-hpc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
create_instance is one line of Ns Hpc's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →