reference_audit
Audit asset references — find unused assets or circular dependencies.
This record as markdown: /tools/quangdang46-uefn-verse-mcp/reference-audit.md
What reference_audit does on Uefn
AI agents call reference_audit to retrieve information from Uefn without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why reference_audit is rated Low
The tool audits and analyzes existing assets to identify unused references or circular dependencies. This is a passive inspection activity with no side effects, reversible changes, code execution, data deletion, or financial impact. It retrieves information about asset relationships only.
From the tool's definition Tool performs 'Audit asset references — find unused assets or circular dependencies.' This is a read-only analysis operation that queries and inspects existing asset data without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
The rule that runs reference_audit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Uefn, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For reference_audit, this is the rule to start with:
reference_audit is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Uefn, apply this rule, and every reference_audit call is checked against it from then on.
Questions about reference_audit
Audit asset references — find unused assets or circular dependencies. It is categorised as a Read tool in the Uefn MCP Server, which means it retrieves data without modifying state.
Register the Uefn MCP server in PolicyLayer and add a rule for reference_audit: 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 Uefn. Nothing to install.
reference_audit 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 reference_audit 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 reference_audit. 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.
reference_audit is provided by the Uefn MCP server (quangdang46/uefn-verse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Uefn, and thousands of servers like it.
This server
Across the catalogue