Delete a contact by ID from SparrowDesk
AI agents call delete_contact to permanently remove resources in SparrowDesk — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The delete operation removes data that cannot be restored without external backups. While the blast radius is limited to a single contact record (not a cascading deletion of an entire system), deletion is inherently irreversible and thus classified as Destructive rather than Write. High severity reflects that contact information is often business-critical, though not financial in nature.
From the tool's definition Tool name is 'delete_contact' and description states 'Delete a contact by ID from SparrowDesk' — the verb 'delete' combined with removal of a contact record indicates irreversible data removal.
Attacks that exploit this kind of access
Delete a contact by ID from SparrowDesk. It is categorised as a Destructive tool in the SparrowDesk MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the SparrowDesk MCP server in PolicyLayer and add a rule for delete_contact: 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 SparrowDesk. Nothing to install.
delete_contact 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_contact 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_contact. 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_contact is provided by the SparrowDesk MCP server (sparrowdesk/sparrowdesk-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 →