Delete a file attachment from a REDCap record field.
AI agents call delete_file to permanently remove resources in Redcap — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting file attachments from research data records is a destructive action that cannot be undone. In a REDCap context managing research data, file deletion could result in loss of critical documentation, consent forms, lab results, or other essential study records. The high severity reflects the potential impact on research data integrity and compliance in a regulated research environment.
From the tool's definition Tool name is 'delete_file' and description states it will 'Delete a file attachment from a REDCap record field' — this is an irreversible deletion operation.
Attacks that exploit this kind of access
Delete a file attachment from a REDCap record field. It is categorised as a Destructive tool in the Redcap MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Redcap MCP server in PolicyLayer and add a rule for delete_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 Redcap. Nothing to install.
delete_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 delete_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 delete_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.
delete_file is provided by the Redcap MCP server (msicilia/mcp-server-redcap). 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 →