Scan the codebase for architectural drift against stored memories.
AI agents call audit_codebase to retrieve information from myBrAIn without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads the codebase and compares it against stored architectural rules/memories. It does not modify, execute, or delete anything. However, severity is medium because it has broad read access to the entire codebase, which could expose sensitive code, secrets, or proprietary logic if misused.
From the tool's definition "Scan the codebase for architectural drift against stored memories" — scanning/auditing implies reading and comparing, no modification indicated
Documented attack patterns abuse exactly the kind of access audit_codebase gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and myBrAIn, and nothing reaches the server without passing your rules. This is the rule we recommend for audit_codebase:
{
"version": "1",
"default": "deny",
"tools": {
"audit_codebase": {}
}
}audit_codebase 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.
Scan the codebase for architectural drift against stored memories. It is categorised as a Read tool in the myBrAIn MCP Server, which means it retrieves data without modifying state.
Register the myBrAIn MCP server in PolicyLayer and add a rule for audit_codebase: 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 myBrAIn. Nothing to install.
audit_codebase 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 audit_codebase 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 audit_codebase. 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.
audit_codebase is provided by the myBrAIn MCP server (lilium360/mybrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from myBrAIn, 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.
5 myBrAIn tools catalogued and risk-classified — across an index of 43,000+ MCP servers.