Return common SAM.gov procurement type and set-aside codes used by the opportunity search tool.
AI agents call sam_reference to retrieve information from DOL WHD MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool simply retrieves and returns reference data (procurement type and set-aside codes) from SAM.gov. It is a pure lookup/read operation with no side effects, no data modification, and no execution of commands. Misuse potential is minimal as it only exposes static reference information.
From the tool's definition Return common SAM.gov procurement type and set-aside codes used by the opportunity search tool
Attacks that exploit this kind of access
Return common SAM.gov procurement type and set-aside codes used by the opportunity search tool. It is categorised as a Read tool in the DOL WHD MCP MCP Server, which means it retrieves data without modifying state.
Register the DOL WHD MCP server in PolicyLayer and add a rule for sam_reference: 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 DOL WHD MCP. Nothing to install.
sam_reference 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 sam_reference 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 sam_reference. 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.
sam_reference is provided by the DOL WHD MCP server (uhq-actual/dol_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 →