Detect drift between AI agent config files (CLAUDE.md, AGENTS.md, .cursorrules) and the live tool/skill/command surface: dead path references, references to non-existent MCP tools, references to missing skills/commands, oversized sections. Convenience alias for
AI agents call check_claudemd_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 is a read-only introspection tool that analyzes and reports on configuration state without modifying anything. It retrieves data about config files and tool surfaces to identify discrepancies. While it could inform refactoring decisions, the tool itself only reads and reports; it does not execute code, delete data, or make changes.
From the tool's definition Tool performs detection and analysis of configuration drift by comparing config files against live tool surfaces. Verifies references exist, identifies dead paths, and scans section sizes.
Documented attack patterns abuse exactly the kind of access check_claudemd_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 check_claudemd_drift:
{
"version": "1",
"default": "deny",
"tools": {
"check_claudemd_drift": {}
}
}check_claudemd_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 drift between AI agent config files (CLAUDE.md, AGENTS.md, .cursorrules) and the live tool/skill/command surface: dead path references, references to non-existent MCP tools, references to missing skills/commands, oversized sections. Convenience alias for. 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 check_claudemd_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.
check_claudemd_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 check_claudemd_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 check_claudemd_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.
check_claudemd_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.