Enforce architecture boundary rules — detect files that import across forbidden layer boundaries. Rules can be passed inline or loaded from .graphhub/arch-rules.json.
AI agents call check_arch_rules to retrieve information from GraphHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
check_arch_rules performs static analysis of a codebase to identify architecture boundary violations. It retrieves and analyzes information about import patterns and layer structure, then reports findings. This is purely informational—it does not execute arbitrary code, modify files, delete data, or trigger external operations.
From the tool's definition Tool description explicitly states it 'detect[s]' violations and 'enforce[s]' rules through analysis. No creation, modification, deletion, execution, or financial operations are described.
Documented attack patterns abuse exactly the kind of access check_arch_rules gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GraphHub, and nothing reaches the server without passing your rules. This is the rule we recommend for check_arch_rules:
{
"version": "1",
"default": "deny",
"tools": {
"check_arch_rules": {}
}
}check_arch_rules 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.
Enforce architecture boundary rules — detect files that import across forbidden layer boundaries. Rules can be passed inline or loaded from .graphhub/arch-rules.json. It is categorised as a Read tool in the GraphHub MCP Server, which means it retrieves data without modifying state.
Register the GraphHub MCP server in PolicyLayer and add a rule for check_arch_rules: 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 GraphHub. Nothing to install.
check_arch_rules 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_arch_rules 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_arch_rules. 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_arch_rules is provided by the GraphHub MCP server (slnquangtran/graph-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GraphHub, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 GraphHub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.