delete_hold
AI agents call delete_hold to permanently remove resources in IBM Content Services MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a legal hold removes an irreversible control mechanism that prevents document destruction and maintains compliance obligations. This cannot be undone and affects document lifecycle management at the enterprise level.
From the tool's definition Tool name 'delete_hold' combined with sibling tools 'create_hold' and 'add_object_to_hold' indicate this irreversibly deletes legal holds from IBM FileNet Content Manager. Legal holds are critical controls for document retention and litigation compliance.
Attacks that exploit this kind of access
delete_hold. It is categorised as a Destructive tool in the IBM Content Services MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the IBM Content Services MCP Server MCP server in PolicyLayer and add a rule for delete_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 IBM Content Services MCP Server. Nothing to install.
delete_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 delete_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 delete_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.
delete_hold is provided by the IBM Content Services MCP Server MCP server (mohamedarif-m/filenet-mcp-localfile). 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 →