AI agents call stream_delete to permanently remove resources in Prometheus MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes entries from a stream, which is an irreversible operation that cannot be undone. This falls squarely into the Destructive category as it destroys data. The high severity reflects that uncontrolled deletion of stream data could result in loss of monitoring/metrics data in a Prometheus context, which could impact observability and operational decision-making.
From the tool's definition Tool name 'stream_delete' combined with description 'Delete entries from stream' explicitly indicates irreversible deletion of data from a stream.
Documented attack patterns abuse exactly the kind of access stream_delete 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 stream_delete:
{
"version": "1",
"default": "deny",
"hide": [
"stream_delete"
]
}stream_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete entries from stream. It is categorised as a Destructive tool in the Prometheus MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Prometheus MCP Server MCP server in PolicyLayer and add a rule for stream_delete: 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.
stream_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the stream_delete 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 stream_delete. 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.
stream_delete 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.