Check architectural layer rules: detect forbidden imports between layers (e.g. domain importing infrastructure). Supports auto-detected presets (clean-architecture, hexagonal) or custom layers. Use to enforce architectural boundaries. Read-only. Returns JSON: { violations: [{ from, to, rule, file...
AI agents call check_architecture 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 analyzes architectural boundaries by inspecting the dependency graph to detect policy violations. It performs static analysis and returns findings without creating, modifying, deleting, or executing code. The 'detect' verb and 'returns JSON' confirm it is a read-only query operation. Low severity because misuse would only surface incorrect architectural reports, not cause damage or execution.
From the tool's definition Tool description explicitly states 'Read-only' and 'detect forbidden imports' (analysis without modification). Returns violations report in JSON. No side effects on source code.
Documented attack patterns abuse exactly the kind of access check_architecture 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_architecture:
{
"version": "1",
"default": "deny",
"tools": {
"check_architecture": {}
}
}check_architecture 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.
Check architectural layer rules: detect forbidden imports between layers (e.g. domain importing infrastructure). Supports auto-detected presets (clean-architecture, hexagonal) or custom layers. Use to enforce architectural boundaries. Read-only. Returns JSON: { violations: [{ from, to, rule, file, line }], total, preset }. 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_architecture: 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_architecture 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_architecture 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_architecture. 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_architecture 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.