Removes items from favorites
AI agents call remove_favorites to permanently remove resources in Smartsheet MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing favorites is an irreversible deletion of the user's saved favorite items. While the blast radius is limited (only affects favorites list, not underlying data), the action cannot be undone through a simple undo mechanism, making it Destructive. Severity is medium because it affects user preferences rather than core data.
From the tool's definition 'Removes items from favorites' — the action is removal/deletion of saved favorite entries
Attacks that exploit this kind of access
Removes items from favorites. It is categorised as a Destructive tool in the Smartsheet MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Smartsheet MCP Server MCP server in PolicyLayer and add a rule for remove_favorites: 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 Smartsheet MCP Server. Nothing to install.
remove_favorites 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_favorites 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_favorites. 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_favorites is provided by the Smartsheet MCP Server MCP server (thomaswtwrt/smar-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 →