AI agents call check_auth_and_credits to retrieve information from Outrank without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves authentication status and credit balance information without modifying any data, executing code, or triggering external operations. It is a straightforward query operation with minimal blast radius if misused by an AI agent—worst case would be information disclosure about the API key validity and remaining credits, which does not affect system integrity or cause irreversible harm.
From the tool's definition Tool name and description indicate 'Verify' and 'retrieve' operations—both read-only actions that query state without modification. No deletion, creation, code execution, or financial transaction is described.
Attacks that exploit this kind of access
Verify the Outrank API key and retrieve remaining article-generation credits. It is categorised as a Read tool in the Outrank MCP Server, which means it retrieves data without modifying state.
Register the Outrank MCP server in PolicyLayer and add a rule for check_auth_and_credits: 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 Outrank. Nothing to install.
check_auth_and_credits 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_auth_and_credits 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_auth_and_credits. 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_auth_and_credits is provided by the Outrank MCP server (nobanks/outrank-mcp). 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 →