delete_relation_tool
AI agents call delete_relation_tool to permanently remove resources in Reltio MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool name contains 'delete', which maps directly to the Destructive category (irreversibly deletes data). Although the description is empty, the name combined with the context of a master data management system makes it clear this tool removes relationship data that cannot be undone.
From the tool's definition Tool name is 'delete_relation_tool' which explicitly performs deletion. Operates on Reltio's master data management platform where relationships between entities are critical data structures. Deletion is irreversible.
Attacks that exploit this kind of access
delete_relation_tool. It is categorised as a Destructive tool in the Reltio MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Reltio MCP Server MCP server in PolicyLayer and add a rule for delete_relation_tool: 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 Reltio MCP Server. Nothing to install.
delete_relation_tool 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_relation_tool 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_relation_tool. 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_relation_tool is provided by the Reltio MCP Server MCP server (reltio-ai/reltio-mcp-server). 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 →