Delete a file and all its associated chunks and embeddings from the index.
AI agents call remove_file to permanently remove resources in Local Search MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly deletes indexed data (file, chunks, and embeddings) that cannot be recovered without re-indexing. While the blast radius is contained to the search index rather than production data systems, the destruction is permanent within that scope.
From the tool's definition Tool description states 'Delete a file and all its associated chunks and embeddings from the index' - explicit deletion action that removes data irreversibly.
Attacks that exploit this kind of access
Delete a file and all its associated chunks and embeddings from the index. It is categorised as a Destructive tool in the Local Search MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Local Search MCP Server MCP server in PolicyLayer and add a rule for remove_file: 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 Local Search MCP Server. Nothing to install.
remove_file 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_file 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_file. 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_file is provided by the Local Search MCP Server MCP server (patrickruddiman/local-search-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 →