Delete a research topic and all its data.
AI agents call delete_research_topic to permanently remove resources in Kavi Research Assistant — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool destroys data permanently by deleting an entire research topic and its associated content. This is categorically Destructive rather than Write because the action cannot be undone—deletion is irreversible. The severity is high because an AI agent misusing this tool could permanently erase important research materials, though the blast radius is limited to research topics rather than critical infrastructure.
From the tool's definition The tool explicitly performs "Delete a research topic and all its data," which irreversibly removes data without reversal capability.
Attacks that exploit this kind of access
Delete a research topic and all its data. It is categorised as a Destructive tool in the Kavi Research Assistant MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kavi Research Assistant MCP server in PolicyLayer and add a rule for delete_research_topic: 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 Kavi Research Assistant. Nothing to install.
delete_research_topic 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_research_topic 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_research_topic. 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_research_topic is provided by the Kavi Research Assistant MCP server (machhakiran/kavi-research-assistant-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 →