AI agents use add_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.
Adding an instrument in REDCap creates or modifies project configuration in a reversible way (instruments can be deleted or modified), making this a Write operation rather than Execute. However, severity is high rather than medium because instruments define data collection structures in a research context, and unintended instrument creation could affect study operations and data integrity.
From the tool's definition Tool name 'add_instrument' indicates creation of a new instrument (survey/form) within a REDCap project. The server context shows tools like 'delete_instrument', 'clone_instrument', 'assign_instrument_to_event' and explicit destructive operations…
Attacks that exploit this kind of access
add_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 add_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.
add_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 add_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 add_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.
add_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 →