AI agents call auth_config to retrieve information from Wardrowbe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation that retrieves authentication configuration data. However, the sensitivity is elevated to medium severity because exposed auth configuration (dev_mode flags, OIDC endpoints, and related credentials) could enable attackers to bypass authentication, downgrade security (via dev_mode), or pivot to identity provider attacks.
From the tool's definition Tool returns auth configuration including dev_mode flag and OIDC settings. Description explicitly states 'Return' indicating data retrieval with no modification capability.
Attacks that exploit this kind of access
Return Wardrowbe's auth configuration (dev_mode flag, OIDC settings). It is categorised as a Read tool in the Wardrowbe MCP Server, which means it retrieves data without modifying state.
Register the Wardrowbe MCP server in PolicyLayer and add a rule for auth_config: 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 Wardrowbe. Nothing to install.
auth_config 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 auth_config 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 auth_config. 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.
auth_config is provided by the Wardrowbe MCP server (saya6k/mcp-wardrowbe). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →