${INSTRUCTIONS_FIRST_GUIDANCE}
AI agents call delete_items to permanently remove resources in Dynalist — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of items from a document is an irreversible operation that destroys data. While Dynalist may offer version history recovery (evidenced by 'check_document_versions' sibling tool), the delete action itself permanently removes items from the current document state. This is categorized as Destructive rather than Write because the operation cannot be easily reversed through the API.
From the tool's definition Tool name 'delete_items' indicates irreversible deletion of data from Dynalist documents. The sibling tools 'create_document', 'edit_items', and 'insert_items' are reversible operations, but deletion cannot be undone without version history intervention.
Attacks that exploit this kind of access
${INSTRUCTIONS_FIRST_GUIDANCE}. It is categorised as a Destructive tool in the Dynalist MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dynalist MCP server in PolicyLayer and add a rule for delete_items: 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 Dynalist. Nothing to install.
delete_items 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_items 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_items. 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_items is provided by the Dynalist MCP server (wawworld/dynalist-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 →