Find exported public symbols with no matching test file — test coverage gaps. For deeper analysis including non-exported symbols use get_untested_symbols instead. Read-only. Returns JSON: { untested: [{ symbol_id, name, kind, file }], total }. Set
AI agents call get_untested_exports to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure query/analysis tool that retrieves information about test coverage from the codebase. It performs no mutations, no code execution, and no side effects. The highest risk is information disclosure (knowing which exports lack tests), which is informational rather than operationally harmful. Confidence is high because the description explicitly labels it as read-only.
From the tool's definition Tool description explicitly states 'Read-only' and 'Find exported public symbols with no matching test file'. Returns JSON data about test coverage gaps without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access get_untested_exports gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for get_untested_exports:
{
"version": "1",
"default": "deny",
"tools": {
"get_untested_exports": {}
}
}get_untested_exports is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find exported public symbols with no matching test file — test coverage gaps. For deeper analysis including non-exported symbols use get_untested_symbols instead. Read-only. Returns JSON: { untested: [{ symbol_id, name, kind, file }], total }. Set. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for get_untested_exports: 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.
get_untested_exports 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_untested_exports 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_untested_exports. 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_untested_exports 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.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.