Skip to main content
Glama
Observium MCP Server

Observium MCP Server

by kdesch5000

get_trends

Retrieve historical trend data for device CPU, memory, load, or uptime across selectable periods, returning time-series values with min, max, avg, and current statistics.

Instructions

Get historical trend data for device metrics.

Returns time-series data for CPU, memory, load, or uptime with statistics. Data comes from RRD files updated every 5 minutes by Observium polling.

RETURNS:

  • hostname, metric, period

  • datasources: What values are in the data (e.g., load1, load5, load15)

  • data_points: Number of samples

  • statistics: For each datasource - min, max, avg, current

  • data: Array of timestamped values (last 100 points)

METRICS:

  • load: System load average (load1, load5, load15)

  • cpu: CPU utilization percentage

  • memory: Memory usage percentage or bytes

  • uptime: System uptime in seconds

PERIODS: 1h, 6h, 1d (default), 1w, 1m

EXAMPLE QUESTIONS:

  • "What's the CPU trend on the server this week?"

  • "Show load average history for the firewall"

  • "What was peak memory usage this month?"

  • "How has uptime looked over the past week?"

TIP: Use list_available_metrics first to see what data exists for a device

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "hostname": "<hostname>"
    },
    "name": "get_trends"
  }
}

Input Schema

NameRequiredDescriptionDefault
metricNoType of metric to retrieveload
periodNoTime period for historical data1d
hostnameYesThe device hostname
device_idNoThe device ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does well: it discloses the data source (RRD files refreshed every 5 minutes by Observium polling) and an implicit result cap ('last 100 points'). It does not discuss permissions, error behavior, or whether the read is side-effect free beyond the 'Get' verb.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Sectioned headers (RETURNS, METRICS, PERIODS, EXAMPLE QUESTIONS, TIP) make it skimmable and the purpose is front-loaded. The example questions are somewhat padded, but each block contributes information an agent would otherwise have to probe for.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, describing the return shape (datasources, data_points, statistics with min/max/avg/current, 100-point data array) is exactly the right compensation, and data freshness is covered. The remaining gap is the hostname/device_id relationship and what happens if a metric is unavailable for a device.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the METRICS section adds genuine meaning by explaining what each enum value yields (load1/5/15 datasources, CPU percentage, memory as percentage or bytes, uptime in seconds). However, the two identifier parameters (hostname vs device_id) are never distinguished, and the 100-point limit is not tied to any parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening line states a specific verb and resource ('Get historical trend data for device metrics') and the METRICS/PERIODS sections pin down exactly what dimensions are covered. It also implicitly differentiates from list_available_metrics by positioning that tool as the discovery step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The TIP explicitly routes the agent to list_available_metrics first, and the EXAMPLE QUESTIONS show the kinds of requests this tool answers. It stops short of naming alternatives or exclusions, e.g. it never says to use get_port_traffic instead for interface-level traffic trends.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.