Skip to main content
Glama
Zabbix MCP Server

Zabbix MCP Server

by mhajder

Proxy Get

proxy_get
Read-onlyIdempotent

Retrieve Zabbix proxy records to inspect or manage data collection points, including paging, filtering, sorting, and optional count-only results.

Instructions

Get proxies from Zabbix.

Proxies act as data collection points for Zabbix, allowing monitoring of remote networks without direct connectivity. Proxies collect data locally and report to the Zabbix server.

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": "proxy_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': 'proxy1'}. Zabbix 7.0 renamed the proxy 'host' field to 'name' and rejects the old one.
proxyidsNoList of proxy IDs to get. Omit to return all proxies; an empty list matches none.
sortfieldNoField to sort by. A deterministic sort is required for paging to be consistent.proxyid
sortorderNoSort direction - 'ASC' or 'DESC'.ASC
count_outputNoIf true, returns only the count of matched objects as an integer.
filter_paramsNoAdditional filter parameters for advanced filtering.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.1
    • changedInput schema / properties / proxyids / description
      Previous value: -"List of proxy IDs to get. If empty, returns all proxies."New value: +"List of proxy IDs to get. Omit to return all proxies; an empty list matches none."
  2. Changed6 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."
    • changedInput schema / properties / search / description
      Previous value: -"Dictionary with search criteria like {'host': 'proxy1'} for name matching."New value: +"Dictionary with search criteria like {'name': 'proxy1'}. Zabbix 7.0\n    renamed the proxy 'host' field to 'name' and rejects the old one."
    • removedInput schema / properties / sortfield / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • changedInput schema / properties / sortfield / default
      Previous value: -nullNew value: +"proxyid"
    • 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 safety is covered structurally. The description adds only encyclopedic context about what proxies do; it says nothing about pagination behaviour, result ordering, whether an empty proxyids list matches nothing, or which Zabbix version quirks apply — all of which are behavioural and would warrant credit.

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?

Front-loaded with the action in the first four words, then three short sentences with no redundancy. The two explanatory sentences are optional background rather than wasted space, but they push the operational content out of the way slightly.

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?

Output schema exists and annotations cover safety, so the description does not need to explain return values. However, for a 9-parameter paged list tool with a version-dependent search field, the description leaves the agent without any operational framing beyond a definition of proxies.

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 89%, so the schema already carries the parameter meaning (limit/offset defaults, search rename from host to name in 7.0, empty-list semantics). The description adds nothing about any of the 9 parameters, so the baseline 3 applies rather than a higher score.

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?

States a specific verb and resource ('Get proxies from Zabbix') and follows with a plain-language definition of what a proxy is, so an agent unfamiliar with Zabbix can place the resource. It does not explicitly contrast itself with proxy_create/proxy_update/proxy_delete, though the read-only verb makes the distinction easy to infer.

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 guidance on when to call this versus other retrieval tools, no mention of the paging pattern (limit/offset/sortfield), no guidance on proxyids vs search vs filter_params, and no mention of when count_output should be preferred. The only 'usage' content is domain background, not invocation routing.

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