Cancels (annuls) a document in Oblio via PUT /api/docs/{type}/cancel.
AI agents call cancel_document to permanently remove resources in Oblio — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although technically a state change rather than deletion, document cancellation in accounting software (especially in the context of e-Factura submission to Romania's SPV system) is an irreversible action that annuls a document's legal and financial standing.
From the tool's definition Tool description explicitly states it 'Cancels (annuls) a document' via PUT endpoint to a cancel action. Cancellation of financial/accounting documents is irreversible in most systems and represents annulment of the document's validity.
Attacks that exploit this kind of access
Cancels (annuls) a document in Oblio via PUT /api/docs/{type}/cancel. It is categorised as a Destructive tool in the Oblio MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Oblio MCP server in PolicyLayer and add a rule for cancel_document: 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 Oblio. Nothing to install.
cancel_document 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 cancel_document 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 cancel_document. 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.
cancel_document is provided by the Oblio MCP server (valentinludu/oblio-mcp). 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 →