Find functions with high complexity called from many files — candidates for extraction to shared modules. Use during architecture review to identify hotspots worth refactoring. Read-only. Returns JSON: [{ symbol_id, name, file, cyclomatic, callerCount }]. Set
AI agents call get_refactor_candidates 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 tool queries and analyzes source code to identify refactoring opportunities, returning metrics like cyclomatic complexity and caller counts. It performs no write, deletion, execution, or financial operations. The 'read-only' designation and passive analysis nature confirm it belongs in the Read category with low severity.
From the tool's definition Tool name 'get_refactor_candidates' and description explicitly states 'Read-only' and 'Find functions with high complexity called from many files'. Returns analysis data in JSON format without modifying code.
Documented attack patterns abuse exactly the kind of access get_refactor_candidates 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_refactor_candidates:
{
"version": "1",
"default": "deny",
"tools": {
"get_refactor_candidates": {}
}
}get_refactor_candidates 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 functions with high complexity called from many files — candidates for extraction to shared modules. Use during architecture review to identify hotspots worth refactoring. Read-only. Returns JSON: [{ symbol_id, name, file, cyclomatic, callerCount }]. 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_refactor_candidates: 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_refactor_candidates 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_refactor_candidates 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_refactor_candidates. 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_refactor_candidates 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.