AI agents call check_field_references to retrieve information from Redcap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to examine or verify field references in a REDCap project without modifying state. Based on naming convention, this is consistent with Read operations (query, check, audit). The empty description and absence of modifying verbs (add, delete, update) support this classification.
From the tool's definition Tool name 'check_field_references' indicates a query/verification operation. The suffix 'check_' and 'references' suggest reading or auditing relationships rather than modifying data. Empty description lowers specificity.
Attacks that exploit this kind of access
check_field_references. It is categorised as a Read tool in the Redcap MCP Server, which means it retrieves data without modifying state.
Register the Redcap MCP server in PolicyLayer and add a rule for check_field_references: 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.
check_field_references is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_field_references 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 check_field_references. 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.
check_field_references 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 →