AI agents call get-health-local-alarms to retrieve information from Rabbitmq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the health status of local alarms in RabbitMQ, returning diagnostic information. It performs a read-only operation with no side effects—no data is created, modified, deleted, or executed. The low severity reflects that misuse would only expose existing health/alarm information, not cause operational harm or data loss.
From the tool's definition Tool name 'get-health-local-alarms' uses 'get' verb indicating a retrieval operation. Description states 'Get health check status' which retrieves monitoring/diagnostic information without modifying state.
Attacks that exploit this kind of access
Get health check status for local alarms. It is categorised as a Read tool in the Rabbitmq MCP Server, which means it retrieves data without modifying state.
Register the Rabbitmq MCP server in PolicyLayer and add a rule for get-health-local-alarms: 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 Rabbitmq. Nothing to install.
get-health-local-alarms 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-health-local-alarms 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-health-local-alarms. 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-health-local-alarms is provided by the Rabbitmq MCP server (rabbitmq-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 →