Deletes (trashes) a single subsample
AI agents call delete_subsample to permanently remove resources in RSpace MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs a destructive action by deleting a subsample from RSpace, which removes research data that cannot be recovered (even if moved to trash, this represents permanent removal from active research). The blast radius is high because deletion of experimental subsamples could compromise research integrity, cause loss of scientific records, or violate data retention policies.
From the tool's definition Tool name 'delete_subsample' and description 'Deletes (trashes) a single subsample' directly indicate irreversible deletion of research data.
Attacks that exploit this kind of access
Deletes (trashes) a single subsample. It is categorised as a Destructive tool in the RSpace MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RSpace MCP Server MCP server in PolicyLayer and add a rule for delete_subsample: 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 RSpace MCP Server. Nothing to install.
delete_subsample is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_subsample 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 delete_subsample. 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.
delete_subsample is provided by the RSpace MCP Server MCP server (rspace-os/rspace-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 →