AI agents use archive_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 modifies the operational state of a sandbox instance by archiving it and disabling new submissions. While the operation is reversible (instances can typically be unarchived or recreated), it significantly impacts the availability and usability of HPC resources.
From the tool's definition 'Archive a sandbox instance, disabling new job submissions' indicates a state change operation that modifies instance status from active to archived, preventing future job submissions.
Attacks that exploit this kind of access
Archive a sandbox instance, disabling new job submissions. 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 archive_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.
archive_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 archive_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 archive_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.
archive_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →