AI agents call list_instances to retrieve information from Ns Hpc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about existing sandbox instances without creating, modifying, deleting, or executing any operations. It is a pure read operation with minimal security risk—exposing the list of active instances poses negligible blast radius compared to tools that execute commands or manage resources.
From the tool's definition Tool name 'list_instances' and description 'List all active (non-archived) sandbox instances' indicate a query/enumeration operation with no side effects.
Attacks that exploit this kind of access
List all active (non-archived) sandbox instances. It is categorised as a Read tool in the Ns Hpc MCP Server, which means it retrieves data without modifying state.
Register the Ns Hpc MCP server in PolicyLayer and add a rule for list_instances: 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.
list_instances 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 list_instances 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 list_instances. 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.
list_instances 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 →