Delete the workflow index (ChromaDB collections).
AI agents call clear_index to permanently remove resources in Ghidra Api — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes the workflow index (ChromaDB collections), which cannot be undone. This is an irreversible destructive action on stored data. While the blast radius is limited to the index itself (not production systems or financial data), destruction of the searchable API documentation index would severely impact the functionality of this MCP server for all users until it is rebuilt.
From the tool's definition Delete the workflow index (ChromaDB collections) - explicitly states 'Delete' which is an irreversible operation that removes data
Attacks that exploit this kind of access
Delete the workflow index (ChromaDB collections). It is categorised as a Destructive tool in the Ghidra Api MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ghidra Api MCP server in PolicyLayer and add a rule for clear_index: 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 Ghidra Api. Nothing to install.
clear_index 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 clear_index 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 clear_index. 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.
clear_index is provided by the Ghidra Api MCP server (taardisaa/ghidra-api-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 →