delete_instrument
AI agents call delete_instrument 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 an instrument from a REDCap project removes an entire survey/form and all associated data irreversibly. This cannot be undone through normal operations and affects all records using that instrument. This is a Destructive action (more severe than Write) because it removes data permanently.
From the tool's definition Tool name 'delete_instrument' combined with sibling tools including 'delete_arms', 'delete_events', 'delete_file', and 'delete_records' on a REDCap server (research data management system). The 'delete_' prefix indicates irreversible removal of data.
Attacks that exploit this kind of access
delete_instrument. 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_instrument: 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_instrument 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_instrument 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_instrument. 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_instrument 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 →