Get alert configurations for the user
AI agents call get_alerts_configuration to retrieve information from Unusual Whales MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user alert configurations, which is a read-only operation. It queries existing data without side effects, making it a Read category tool. The severity is low because access to alert configuration data presents minimal risk—it does not modify state, execute operations, or impact financial transactions.
From the tool's definition Tool name 'get_alerts_configuration' and description 'Get alert configurations for the user' indicate retrieval of existing configuration data with no modification or execution.
Attacks that exploit this kind of access
Get alert configurations for the user. It is categorised as a Read tool in the Unusual Whales MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Unusual Whales MCP Server MCP server in PolicyLayer and add a rule for get_alerts_configuration: 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 Unusual Whales MCP Server. Nothing to install.
get_alerts_configuration 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_alerts_configuration 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_alerts_configuration. 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_alerts_configuration is provided by the Unusual Whales MCP Server MCP server (phields/unusualwhales-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 →