AI agents call get_sdtm_variable to retrieve information from Cdisc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves standardized variable definitions from the CDISC Library API. It performs a simple lookup without creating, modifying, deleting, or executing any operations. The operation is informational only and carries minimal security risk — misuse would only result in unwanted access to public standards documentation.
From the tool's definition Tool description states 'Get the full definition of a specific SDTM variable' — a retrieval operation with no modification or execution of data.
Attacks that exploit this kind of access
Get the full definition of a specific SDTM variable. It is categorised as a Read tool in the Cdisc MCP Server, which means it retrieves data without modifying state.
Register the Cdisc MCP server in PolicyLayer and add a rule for get_sdtm_variable: 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 Cdisc. Nothing to install.
get_sdtm_variable 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 get_sdtm_variable 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 get_sdtm_variable. 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.
get_sdtm_variable is provided by the Cdisc MCP server (teninq/cdisc-mcp). 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 →