Delete multiple relations from the knowledge graph.
AI agents call delete_relations to permanently remove resources in Rawthink — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes relations (edges/connections) from a knowledge graph with no apparent undo mechanism. Deletion is irreversible and destructive. While not financial, it ranks higher than Write/Execute because it destroys data that cannot be recovered.
From the tool's definition Tool name 'delete_relations' and description 'Delete multiple relations from the knowledge graph' explicitly indicate irreversible deletion of data structures from a persistent knowledge graph.
Attacks that exploit this kind of access
Delete multiple relations from the knowledge graph. It is categorised as a Destructive tool in the Rawthink MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Rawthink MCP server in PolicyLayer and add a rule for delete_relations: 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 Rawthink. Nothing to install.
delete_relations 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_relations 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_relations. 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_relations is provided by the Rawthink MCP server (ygtalp/rawthink-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 →