dc_reference_lookup
AI agents call dc_reference_lookup to retrieve information from Datacenter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve reference data for data center engineering calculations (e.g., standards tables, thermal properties, material specs). The 'lookup' nomenclature strongly implies read-only querying. However, confidence is moderate (0.7) rather than high because the description is empty, leaving some ambiguity about actual implementation.
From the tool's definition Tool name 'dc_reference_lookup' suggests a read-only reference query operation. The name pattern (lookup) and context among engineering calculation tools indicate data retrieval without modification or execution.
Attacks that exploit this kind of access
dc_reference_lookup. It is categorised as a Read tool in the Datacenter MCP Server, which means it retrieves data without modifying state.
Register the Datacenter MCP server in PolicyLayer and add a rule for dc_reference_lookup: 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 Datacenter. Nothing to install.
dc_reference_lookup 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 dc_reference_lookup 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 dc_reference_lookup. 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.
dc_reference_lookup is provided by the Datacenter MCP server (log-wade/datacenter-mcp-server). 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 →