Delete a block by ID
AI agents call delete_block to permanently remove resources in Wolai MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes blocks from a Wolai knowledge base without reversal capability. Deletion is an irreversible operation that destroys data, placing it in the Destructive category. Given that blocks are content units in a knowledge base system and their deletion cannot be undone, the severity is high. Confidence is high due to explicit 'delete' terminology and clear destructive semantics.
From the tool's definition Tool name 'delete_block' explicitly indicates deletion operation. Description states 'Delete a block by ID', confirming irreversible removal of data.
Attacks that exploit this kind of access
Delete a block by ID. It is categorised as a Destructive tool in the Wolai MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Wolai MCP Server MCP server in PolicyLayer and add a rule for delete_block: 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 Wolai MCP Server. Nothing to install.
delete_block 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_block 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_block. 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_block is provided by the Wolai MCP Server MCP server (wuchaoli/wolai-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 →