Skip to main content
Glama
Zabbix MCP Server

Zabbix MCP Server

by mhajder

Problem Get

problem_get
Read-onlyIdempotent

Retrieve active Zabbix problems with filters for hosts, groups, triggers, severity, time range, and acknowledgment status to identify and page through monitored infrastructure issues.

Instructions

Get problems from Zabbix.

Problems are active trigger states that indicate issues with monitored infrastructure. Each problem is associated with a trigger and can be acknowledged by operators.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "problem_get"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of results to return. Default is 100.
offsetNoNumber of matching records to skip. Use with 'limit' to page through results; check 'has_more' and 'total' in the response.
outputNoextend
recentNoIf true, only return recently recovered problems.
searchNoDictionary with search criteria like {'name': 'CPU'}.
hostidsNoList of host IDs to get problems from. An empty list matches none.
eventidsNoList of event IDs to get problems for. Omit to return all problems; an empty list matches none.
groupidsNoList of host group IDs to get problems from. An empty list matches none.
objectidsNoList of trigger IDs to get problems from. An empty list matches none.
sortfieldNoField to sort by. A deterministic sort is required for paging to be consistent.eventid
sortorderNoSort direction - 'ASC' or 'DESC'.ASC
time_fromNoUnix timestamp.
time_tillNoUnix timestamp.
severitiesNoSeverity levels 0-5.
suppressedNoIf false, return only unsuppressed problems. If true, return only suppressed problems.
acknowledgedNoIf false, return only unacknowledged problems. If true, return only acknowledged problems.
count_outputNoIf true, returns only the count of matched objects as an integer.
select_hostsNoIf true, each problem includes a 'hosts' list (hostid, host, name) of the hosts it occurred on.
name_containsNoShortcut to search for problems by name (constructs search={'name': name_contains}).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.0
    • addedInput schema / properties / select_hosts
      Added value: +{
      +  "default": false,
      +  "description": "If true, each problem includes a 'hosts' list (hostid, host, name) of the hosts it occurred on.",
      +  "type": "boolean"
      +}
  2. Changed4 schema fields changedv0.7.1
    • changedInput schema / properties / eventids / description
      Previous value: -"List of event IDs to get problems for. If empty, returns all problems."New value: +"List of event IDs to get problems for. Omit to return all problems; an empty list matches none."
    • changedInput schema / properties / groupids / description
      Previous value: -"List of host group IDs to get problems from."New value: +"List of host group IDs to get problems from. An empty list matches none."
    • changedInput schema / properties / hostids / description
      Previous value: -"List of host IDs to get problems from."New value: +"List of host IDs to get problems from. An empty list matches none."
    • changedInput schema / properties / objectids / description
      Previous value: -"List of trigger IDs to get problems from."New value: +"List of trigger IDs to get problems from. An empty list matches none."
  3. Changed5 schema fields changedv0.6.0
    • changedInput schema / properties / offset / description
      Previous value: -"Number of results to skip (for pagination). Requires sortfield to be set."New value: +"Number of matching records to skip. Use with 'limit' to page through results; check 'has_more' and 'total' in the response."
    • removedInput schema / properties / sortfield / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • changedInput schema / properties / sortfield / default
      Previous value: -nullNew value: +"eventid"
    • changedInput schema / properties / sortfield / description
      Previous value: -"Field to sort by."New value: +"Field to sort by. A deterministic sort is required for paging to be consistent."
    • addedInput schema / properties / sortfield / type
      Added value: +"string"
  4. First observedv0.5.3

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful domain semantics (active trigger states, acknowledgement by operators) but says nothing about default result limits, paging consistency, or the effect of the many filters — context that matters for a 19-parameter list tool.

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?

Three short sentences, front-loaded with the action, then domain context. No waste, though the explanatory sentences are informational rather than operational and could have carried an alternative-tool pointer instead.

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

Completeness3/5

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

With an output schema present and 95% schema coverage, the description needn't explain return values. But for a high-parameter, high-traffic query tool sitting among trigger_get, event_get and event_acknowledge, the missing selection guidance leaves a real gap.

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 description coverage is 95%, so nearly every parameter is already documented in-schema (limit/offset paging, sortfield determinism, empty-list semantics, name_contains shortcut). The description adds no parameter-level meaning beyond that, which is the expected baseline when the schema does the heavy lifting.

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

Purpose4/5

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

The description states a specific verb and resource ("Get problems from Zabbix") and adds domain framing: problems are active trigger states tied to a trigger and acknowledgeable by operators. That is clear, but it never distinguishes this tool from close siblings like trigger_get, event_get, or event_acknowledge, which an agent must choose between.

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

Usage Guidelines2/5

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

There is no when-to-use / when-not-to-use guidance and no named alternative. The agent is left to infer that it should call this instead of event_get or trigger_get when it wants currently active issues, and nothing tells it how acknowledgement state relates to event_acknowledge.

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