Apply a Hammerspace objective using the hs CLI
AI agents invoke apply_hs_objective to trigger actions in Hammerspace Storage Management MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool runs a CLI command ('hs CLI') to apply a storage objective, which constitutes executing an external shell/system command. Objectives in storage management can modify tiering, data placement, retention policies, and other storage behaviors.
From the tool's definition Apply a Hammerspace objective using the hs CLI
Attacks that exploit this kind of access
Apply a Hammerspace objective using the hs CLI. It is categorised as a Execute tool in the Hammerspace Storage Management MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hammerspace Storage Management MCP Server MCP server in PolicyLayer and add a rule for apply_hs_objective: 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 Hammerspace Storage Management MCP Server. Nothing to install.
apply_hs_objective is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the apply_hs_objective 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 apply_hs_objective. 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.
apply_hs_objective is provided by the Hammerspace Storage Management MCP Server MCP server (mbloomhammerspace/mcp-1.5-main). 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 →