AI agents use import_records 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.
This tool creates or modifies data (research records) in a reversible manner, fitting the Write category. Severity is high because REDCap manages sensitive research data; importing records could corrupt studies, affect data integrity, or compromise research validity if misused by an AI agent without proper validation.
From the tool's definition Tool name 'import_records' and description 'Import records into the REDCap project' indicate creation/modification of research data records. The context of REDCap (a research data management system) means these are production research datasets.
Attacks that exploit this kind of access
Import records into the REDCap project. 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 import_records: 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.
import_records 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 import_records 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 import_records. 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.
import_records 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 →