Code hotspots: files with both high complexity AND high git churn (Adam Tornhill methodology). Score = complexity × log(1 + commits). Each entry includes a confidence_level (low/medium/multi_signal) counting how many of the two independent signals fired strongly. Result envelope includes _methodo...
AI agents call get_risk_hotspots 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.
get_risk_hotspots retrieves and analyzes existing source code metrics and version control history to identify problematic files. It performs no mutations, deletions, executions, or financial operations. The tool is purely informational—it reads git data and code metrics to produce a prioritization report for refactoring decisions.
From the tool's definition Tool description explicitly states 'Read-only' and returns analysis data without side effects. It queries code complexity metrics and git history to identify hotspots using Adam Tornhill methodology.
Documented attack patterns abuse exactly the kind of access get_risk_hotspots 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_risk_hotspots:
{
"version": "1",
"default": "deny",
"tools": {
"get_risk_hotspots": {}
}
}get_risk_hotspots 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.
Code hotspots: files with both high complexity AND high git churn (Adam Tornhill methodology). Score = complexity × log(1 + commits). Each entry includes a confidence_level (low/medium/multi_signal) counting how many of the two independent signals fired strongly. Result envelope includes _methodology disclosure and _warnings when git is unavailable. Requires git. Use to prioritize refactoring. For per-file bug prediction use predict_bugs instead. Read-only. Returns JSON: { hotspots: [{ file, score, complexity, commits, confidence_level }], 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_risk_hotspots: 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_risk_hotspots 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_risk_hotspots 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_risk_hotspots. 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_risk_hotspots 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.