Retrieve metrics data for a specific host from Mackerel. 🔍 USE THIS TOOL WHEN USERS: - Get metrics data for a specific host - Analyze host performance over time 📊 AVAILABLE METRIC NAMES: - Standard metrics (mackerel-agent): loadavg5, cpu.user, memory.used, disk.sda1.reads, network.eth0.rxBytes,...
AI agents call get_host_metrics to retrieve information from Mackerel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves monitoring metrics data without side effects. It performs a query operation on existing host performance data, consistent with the Read category (search, list, get, fetch). The severity is low because retrieving metrics poses minimal risk even if misused by an agent — it only exposes observability data without enabling state changes or external operations.
From the tool's definition Tool name is 'get_host_metrics' and description states 'Retrieve metrics data for a specific host from Mackerel.' The use cases specify 'Get metrics data' and 'Analyze host performance' — both read-only operations.
Documented attack patterns abuse exactly the kind of access get_host_metrics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mackerel MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_host_metrics:
{
"version": "1",
"default": "deny",
"tools": {
"get_host_metrics": {}
}
}get_host_metrics is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve metrics data for a specific host from Mackerel. 🔍 USE THIS TOOL WHEN USERS: - Get metrics data for a specific host - Analyze host performance over time 📊 AVAILABLE METRIC NAMES: - Standard metrics (mackerel-agent): loadavg5, cpu.user, memory.used, disk.sda1.reads, network.eth0.rxBytes, etc. - Custom metrics: custom.myapp.* (user-defined metrics) - AWS integration: ec2.cpu.used, rds.database_connections.used, etc. - Azure integration: azure.virtual_machine.cpu.percent, azure.sql_database.cpu.percent, etc. - GCP integration: gce.instance.cpu.used, etc. <examples> Get CPU load average for a host \. It is categorised as a Read tool in the Mackerel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mackerel MCP Server MCP server in PolicyLayer and add a rule for get_host_metrics: 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 Mackerel MCP Server. Nothing to install.
get_host_metrics 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_host_metrics 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_host_metrics. 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_host_metrics is provided by the Mackerel MCP Server MCP server (mackerelio-labs/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mackerel 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.
16 Mackerel MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.