self_audit

SERVERTrace SOURCEnikolai-vysotskyi/trace-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/nikolai-vysotskyi-trace-mcp/self-audit.md

WHAT IT DOES

What self_audit does on Trace

AI agents call self_audit to retrieve information from Trace without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why self_audit is rated Low

Performs static analysis audit without modifying code or executing operations.

From the tool's definition Read-only health check; dead exports, untested symbols, heritage debt analysis.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs self_audit safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Trace, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For self_audit, this is the rule to start with:

self_audit Allowed

self_audit is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "self_audit": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Trace, apply this rule, and every self_audit call is checked against it from then on.

FAQ

Questions about self_audit

What does the self_audit tool do? +

Dead code & coverage audit: dead exports, untested public symbols, heritage debt. Use as a one-shot health check combining dead exports + untested symbols + heritage debt. For individual checks use get_dead_code or get_untested_symbols separately. Read-only. Returns JSON: { deadExports, untestedSymbols, heritageDebt, summary }. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on self_audit? +

Register the Trace MCP server in PolicyLayer and add a rule for self_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 Trace. Nothing to install.

What risk level is self_audit? +

self_audit is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit self_audit? +

Yes. Add a rate_limit block to the self_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.

How do I block self_audit completely? +

Set action: deny in the PolicyLayer policy for self_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.

What MCP server provides self_audit? +

self_audit is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Trace, and thousands of servers like it.

This server

All 191 Trace tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →