Execute a PromQL query against Amazon Managed Prometheus. ## Usage - Use this tool to execute a PromQL query at a specific instant in time - The query will return the current value of the specified metrics - For time series data over a range, use execute_range_query instead - If workspace_id is ...
Accepts freeform code/query input (query); Single-target operation
Part of the Prometheus MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents invoke ExecuteQuery to trigger processes or run actions in Prometheus MCP Server. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
ExecuteQuery can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
tools:
ExecuteQuery:
rules:
- action: allow
rate_limit:
max: 10
window: 60
validate:
required_args: trueSee the full Prometheus MCP Server policy for all 5 tools.
Agents calling execute-class tools like ExecuteQuery have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
ExecuteQuery is one of the high-risk operations in Prometheus MCP Server. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.
Execute a PromQL query against Amazon Managed Prometheus. ## Usage - Use this tool to execute a PromQL query at a specific instant in time - The query will return the current value of the specified metrics - For time series data over a range, use execute_range_query instead - If workspace_id is not known, use GetAvailableWorkspaces tool first to find available workspaces and ASK THE USER to choose one - Uses DescribeWorkspace API to get the exact workspace URL - No manual URL construction is performed ## Example Input: workspace_id: "ws-12345678-abcd-1234-efgh-123456789012" query: "up" region: "us-east-1" Output: { "resultType": "vector", "result": [ { "metric": {"__name__": "up", "instance": "localhost:9090", "job": "prometheus"}, "value": [1680307200, "1"] }, { "metric": {"__name__": "up", "instance": "localhost:9100", "job": "node"}, "value": [1680307200, "1"] } ] } Example queries: - `up` - Shows which targets are up - `rate(node_cpu_seconds_total{mode="system"}[1m])` - CPU usage rate - `sum by(instance) (rate(node_network_receive_bytes_total[5m]))` - Network receive rate by instance. 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.
Add a rule in your Intercept YAML policy under the tools section for ExecuteQuery. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Prometheus MCP Server MCP server.
ExecuteQuery 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 ExecuteQuery rule in your Intercept 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 Intercept policy for ExecuteQuery. 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.
ExecuteQuery is provided by the Prometheus MCP Server MCP server (awslabs.prometheus-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.