AI agents call analyze_metric to retrieve information from AWS HealthImaging MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'analyze_metric' implies retrieving and examining metric data without side effects. No destructive, financial, or write operations are evident from the name alone. Given the empty description and the sibling tools on the AWS HealthImaging server (which include read operations like 'aggregate' and write operations like 'add_attachments_to_set'), this most likely performs metric analysis/retrieval.
From the tool's definition Tool name 'analyze_metric' suggests data querying/inspection with no modification. Description is empty, limiting confidence.
Documented attack patterns abuse exactly the kind of access analyze_metric gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS HealthImaging MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for analyze_metric:
{
"version": "1",
"default": "deny",
"tools": {
"analyze_metric": {}
}
}analyze_metric is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
analyze_metric. It is categorised as a Read tool in the AWS HealthImaging MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS HealthImaging MCP Server MCP server in PolicyLayer and add a rule for analyze_metric: 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 AWS HealthImaging MCP Server. Nothing to install.
analyze_metric 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 analyze_metric 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 analyze_metric. 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.
analyze_metric is provided by the AWS HealthImaging MCP Server MCP server (awslabs.healthimaging-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS HealthImaging MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
805 AWS HealthImaging MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.