Find deferred work and shortcuts: TODO/FIXME/HACK/XXX comments, empty functions & stubs, hardcoded values (IPs, URLs, credentials, magic numbers, feature flags), debug artifacts (console.log, debugger, var_dump, dd, binding.pry, pdb.set_trace, dbg!, printStackTrace, and 20+ other per-language deb...
AI agents call scan_code_smells 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 static analysis tool that retrieves and reports code patterns and quality metrics. It has no side effects—it does not create, modify, execute, or delete code. The description explicitly contrasts it with other tools (detect_antipatterns for performance, scan_secur for security), confirming it is a read-only scanner.
From the tool's definition scan_code_smells finds and reports code quality issues: TODO/FIXME/HACK/XXX comments, empty functions, hardcoded values, debug artifacts. It 'Surfaces technical debt' and is used for 'code quality audit / pre-release checks'.
Documented attack patterns abuse exactly the kind of access scan_code_smells 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 scan_code_smells:
{
"version": "1",
"default": "deny",
"tools": {
"scan_code_smells": {}
}
}scan_code_smells 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 deferred work and shortcuts: TODO/FIXME/HACK/XXX comments, empty functions & stubs, hardcoded values (IPs, URLs, credentials, magic numbers, feature flags), debug artifacts (console.log, debugger, var_dump, dd, binding.pry, pdb.set_trace, dbg!, printStackTrace, and 20+ other per-language debug markers). Surfaces technical debt that grep alone misses by combining comment scanning, symbol body analysis, and context-aware false-positive filtering. Use for code quality audit / pre-release checks. For performance-specific antipatterns use detect_antipatterns; for security issues use scan_security. Read-only. Returns JSON: { findings: [{ category, priority, file, line, message }], total, summary }. 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 scan_code_smells: 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.
scan_code_smells 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 scan_code_smells 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 scan_code_smells. 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.
scan_code_smells 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.