describe_alarm
AI agents call describe_alarm to retrieve information from Yamcs MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or fetch details about an alarm without modifying state. Despite the empty description, the naming pattern and context within a mission control system (Yamcs) strongly suggests this is a read-only query operation.
From the tool's definition Tool name 'describe_alarm' indicates a retrieval/query operation that returns alarm information. The naming convention aligns with other 'describe_*' sibling tools (describe_command, describe_instance, describe_link) which are non-mutating reads in mission…
Attacks that exploit this kind of access
describe_alarm. It is categorised as a Read tool in the Yamcs MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Yamcs MCP Server MCP server in PolicyLayer and add a rule for describe_alarm: 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 Yamcs MCP Server. Nothing to install.
describe_alarm 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 describe_alarm 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 describe_alarm. 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.
describe_alarm is provided by the Yamcs MCP Server MCP server (paulmramirez/yamcs-mcp-server). 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 →