Release a legal hold.
AI agents call release_legal_hold to permanently remove resources in ComplyOS — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
A legal hold is a formal preservation directive used in litigation or regulatory investigations. Releasing it irreversibly removes the obligation to preserve data, which could result in destruction of legally protected evidence. This is a high-stakes, difficult-to-reverse action with significant legal and regulatory consequences if done improperly.
From the tool's definition 'Release a legal hold' — releasing a legal hold is an irreversible compliance/legal action that removes preservation obligations on data, potentially allowing deletion or modification of evidence that was legally protected
Attacks that exploit this kind of access
Release a legal hold. It is categorised as a Destructive tool in the ComplyOS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ComplyOS MCP server in PolicyLayer and add a rule for release_legal_hold: 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 ComplyOS. Nothing to install.
release_legal_hold 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 release_legal_hold 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 release_legal_hold. 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.
release_legal_hold is provided by the ComplyOS MCP server (simongonzalezdc/complyos). 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 →