list_canaries
AI agents call list_canaries to retrieve information from Amazon SageMaker AI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly suggests it retrieves or enumerates canary configurations or results from AWS CloudWatch Synthetics, which is a non-destructive read operation. Empty description lowers confidence slightly, but the naming convention is clear. Severity is low as listing operations have minimal blast radius even if misused by an AI agent.
From the tool's definition Tool name 'list_canaries' indicates a listing/query operation with no description provided. The 'list_' prefix is characteristic of Read operations that retrieve data without modification.
Attacks that exploit this kind of access
list_canaries. It is categorised as a Read tool in the Amazon SageMaker AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon SageMaker AI MCP Server MCP server in PolicyLayer and add a rule for list_canaries: 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 Amazon SageMaker AI MCP Server. Nothing to install.
list_canaries 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 list_canaries 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 list_canaries. 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.
list_canaries is provided by the Amazon SageMaker AI MCP Server MCP server (awslabs.sagemaker-ai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.