AI agents call get_api_usage to retrieve information from Gurufocus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves API usage metrics, which is a read-only query operation with no side effects. Even though the description is empty, the naming convention strongly suggests it queries usage data without creating, modifying, deleting, or executing operations. The low severity reflects minimal risk from misuse—an agent retrieving usage statistics poses negligible harm.
From the tool's definition Tool name 'get_api_usage' indicates retrieval of usage statistics with no modification capability. No description provided, but the 'get_' prefix and API usage pattern are consistent with Read operations that query system state.
Attacks that exploit this kind of access
get_api_usage. It is categorised as a Read tool in the Gurufocus MCP Server, which means it retrieves data without modifying state.
Register the Gurufocus MCP server in PolicyLayer and add a rule for get_api_usage: 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 Gurufocus. Nothing to install.
get_api_usage 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 get_api_usage 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 get_api_usage. 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.
get_api_usage is provided by the Gurufocus MCP server (u-daveblack/gurufocus-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 →