Remove a tag from an object
AI agents call remove_tag_from_object to permanently remove resources in Sevdesk — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a tag from an object deletes the association between the tag and the object. While the underlying tag and object themselves remain, the association is destroyed without an explicit undo mechanism, making this a Destructive operation. Severity is medium since it affects metadata/classification rather than core financial or business records.
From the tool's definition 'Remove a tag from an object' — removal of a tag association is an irreversible deletion of that relationship
Attacks that exploit this kind of access
Remove a tag from an object. It is categorised as a Destructive tool in the Sevdesk MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sevdesk MCP server in PolicyLayer and add a rule for remove_tag_from_object: 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 Sevdesk. Nothing to install.
remove_tag_from_object 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 remove_tag_from_object 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 remove_tag_from_object. 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.
remove_tag_from_object is provided by the Sevdesk MCP server (codestra/sevdesk-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 →