Detect architectural drift: cross-module co-change anomalies (files in different modules that always change together) and shotgun surgery patterns (commits touching 3+ modules). Requires git. Use to identify hidden coupling across modules. For file-pair co-changes use get_co_changes instead. Read...
AI agents call detect_drift 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 existing git metadata and source code relationships to surface insights about coupling patterns. It retrieves and processes information from the dependency graph and git history but makes no modifications to code, configuration, or any system state. The explicit 'Read-only' designation confirms this is a safe read operation for intelligence gathering and analysis purposes.
From the tool's definition Tool description explicitly states 'Read-only' and performs analysis of existing git history to detect patterns. Returns JSON data without modifying code, configuration, or repository state.
Documented attack patterns abuse exactly the kind of access detect_drift 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 detect_drift:
{
"version": "1",
"default": "deny",
"tools": {
"detect_drift": {}
}
}detect_drift 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.
Detect architectural drift: cross-module co-change anomalies (files in different modules that always change together) and shotgun surgery patterns (commits touching 3+ modules). Requires git. Use to identify hidden coupling across modules. For file-pair co-changes use get_co_changes instead. Read-only. Returns JSON: { anomalies, shotgunSurgery, total }. 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 detect_drift: 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.
detect_drift 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 detect_drift 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 detect_drift. 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.
detect_drift 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.