Skip to main content
Glama
Zabbix MCP Server

Zabbix MCP Server

by mhajder

Graph Get

graph_get
Read-onlyIdempotent

Retrieve Zabbix graphs by graph, host, or template IDs, with optional search, filtering, paging, and related host or item details for monitoring analysis.

Instructions

Get graphs from Zabbix.

Graphs visualize item data over time, displaying metric values in line/bar/pie charts. Graphs can be included in dashboards, reports, and custom views for data analysis.

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": "graph_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
searchNoDictionary with search criteria like {'name': 'CPU'}.
hostidsNoList of host IDs to get graphs from. An empty list matches none.
graphidsNoList of graph IDs to get. Omit to return all graphs; an empty list matches none.
sortfieldNoField to sort by. A deterministic sort is required for paging to be consistent.graphid
sortorderNoSort direction - 'ASC' or 'DESC'.ASC
templateidsNoList of template IDs to get graphs from. An empty list matches none.
count_outputNoIf true, returns only the count of matched objects as an integer.
select_hostsNoIf true, include the hosts that the graphs belong to (selectHosts=extend).
select_itemsNoIf true, include the items contained in each graph (selectGraphItems=extend).
filter_paramsNoAdditional filter parameters for advanced filtering.
select_templatesNoIf true, include the templates that the graphs belong to (selectTemplates=extend).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.7.1
    • changedInput schema / properties / graphids / description
      Previous value: -"List of graph IDs to get. If empty, returns all graphs."New value: +"List of graph IDs to get. Omit to return all graphs; an empty list matches none."
    • changedInput schema / properties / hostids / description
      Previous value: -"List of host IDs to get graphs from."New value: +"List of host IDs to get graphs from. An empty list matches none."
    • changedInput schema / properties / templateids / description
      Previous value: -"List of template IDs to get graphs from."New value: +"List of template IDs to get graphs from. An empty list matches none."
  2. 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: +"graphid"
    • 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"
  3. First observedv0.5.3

TDQS

C2.9/5.0
Behavior2/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is fully covered. The description adds no behavioral context beyond that — no mention of pagination semantics, large-result behavior, or how filtering and select_* flags affect cost/size. The remaining sentences are domain trivia about what graphs are used for, not behavior.

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

Conciseness3/5

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

The first sentence is front-loaded and earns its place. The second paragraph (charts, dashboards, reports, custom views) is generic product blurb that adds no actionable information for an agent and inflates the definition without improving call accuracy.

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?

The schema is rich and an output schema exists, so return values need not be explained. For a 14-parameter read tool with no required args, the description is adequate but thin: it says nothing about paging discipline, how to combine graphids/hostids/templateids, or what count_output returns in context, which are the places an agent is most likely to mis-call.

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 93%, so the 14 parameters (including limit/offset paging, search, ids lists, and select_* flags) are already well documented in structured data. The description contributes no additional parameter meaning, so the baseline 3 applies.

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 opens with a specific verb and resource ("Get graphs from Zabbix"), which unambiguously separates this tool from the other resource-scoped siblings in the list (host_get, item_get, trigger_get). However, it does not sharpen that distinction by explaining what a 'graph' object is relative to its underlying items, leaving only the resource name to differentiate.

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 statement of when to call this tool versus alternatives such as item_get or history_get/trend_get, which return the data that graphs render. The second paragraph describes what graphs are in general terms but gives no selection guidance, exclusions, or prerequisites.

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