Delete multiple entities and their associated relations from the knowledge graph
AI agents call delete_entities to permanently remove resources in Server Sequential Thinking — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data (entities and their relations) from the knowledge graph. Deletion is an irreversible operation that cannot be undone. The tool operates on multiple entities simultaneously, increasing the blast radius.
From the tool's definition Tool description explicitly states 'Delete multiple entities and their associated relations' — uses the word 'Delete' and performs irreversible removal from a knowledge graph with cascading effects on relations.
Attacks that exploit this kind of access
Delete multiple entities and their associated relations from the knowledge graph. It is categorised as a Destructive tool in the Server Sequential Thinking MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Server Sequential Thinking MCP server in PolicyLayer and add a rule for delete_entities: 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 Server Sequential Thinking. Nothing to install.
delete_entities 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_entities 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_entities. 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_entities is provided by the Server Sequential Thinking MCP server (@modelcontextprotocol/server-sequential-thinking). 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 →