AI agents invoke stop_runtime_session to trigger actions in Prometheus MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool performs an action that affects live infrastructure state (stopping a session) rather than reading or writing reversible data. While not destructive in the deletion sense, stopping a session is an Execute-category operation with potential blast radius if triggered inadvertently—it could interrupt monitoring or observability pipelines.
From the tool's definition Tool name 'stop_runtime_session' indicates termination of an active runtime session; combined with Prometheus MCP Server context (AWS Managed Prometheus), this likely triggers external operations with real effects on infrastructure monitoring.
Documented attack patterns abuse exactly the kind of access stop_runtime_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Prometheus MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_runtime_session:
{
"version": "1",
"default": "deny",
"tools": {
"stop_runtime_session": {
"limits": [
{
"counter": "stop_runtime_session_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_runtime_session stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
stop_runtime_session. It is categorised as a Execute tool in the Prometheus MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Prometheus MCP Server MCP server in PolicyLayer and add a rule for stop_runtime_session: 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 Prometheus MCP Server. Nothing to install.
stop_runtime_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop_runtime_session 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 stop_runtime_session. 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.
stop_runtime_session is provided by the Prometheus MCP Server MCP server (awslabs.prometheus-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Prometheus 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 Prometheus MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.