unrelate_decisions
Remove one typed edge between two decisions. Both decisions are untouched — only the edge goes, and only the edge with exactly this relation; a pair related two ways keeps the other edge. Use this when an edge was drawn in error. To say a ruling no longer applies, do not unrelate it: record the s...
This record as markdown: /tools/adrata-adrata-mcp/unrelate-decisions.md
What unrelate_decisions does on Adrata
AI agents call unrelate_decisions to permanently remove resources in Adrata, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why unrelate_decisions is rated Critical
An AI agent that decides to call unrelate_decisions doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Adrata is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs unrelate_decisions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adrata, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For unrelate_decisions, this is the rule to start with:
unrelate_decisions is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Adrata, apply this rule, and every unrelate_decisions call is checked against it from then on.
Questions about unrelate_decisions
Remove one typed edge between two decisions. Both decisions are untouched — only the edge goes, and only the edge with exactly this relation; a pair related two ways keeps the other edge. Use this when an edge was drawn in error. To say a ruling no longer applies, do not unrelate it: record the superseding decision instead, so the history stays. Removing an edge that is already gone is a no-op.${GOVERNED_NOTE}. It is categorised as a Destructive tool in the Adrata MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Adrata MCP server in PolicyLayer and add a rule for unrelate_decisions: 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 Adrata. Nothing to install.
unrelate_decisions 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 unrelate_decisions 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 unrelate_decisions. 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.
unrelate_decisions is provided by the Adrata MCP server (@adrata/adrata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adrata, and thousands of servers like it.
Across the catalogue