AI agents use rename_instrument to create or update resources in Redcap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Redcap environment.
Renaming an instrument in REDCap modifies metadata but does not delete or execute arbitrary code. It is reversible (can be renamed again), making it Write rather than Destructive or Execute. Medium severity reflects that incorrect renames could cause confusion in research workflows and require correction, but the action is not catastrophic and can be undone.
From the tool's definition Tool is named 'rename_instrument' and operates within REDCap, a research data management system. The sibling tools include destructive operations (delete_arms, delete_events, delete_file, delete_instrument, delete_records) and write operations (add_field,…
Attacks that exploit this kind of access
rename_instrument. It is categorised as a Write tool in the Redcap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Redcap MCP server in PolicyLayer and add a rule for rename_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.
rename_instrument is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rename_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 rename_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.
rename_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 →