Skip to main content
Glama
initMAX

Zabbix MCP Server

device_get

Read-only

Retrieve paired Zabbix mobile app devices and their onboarding status, owner, and last access. Filter by device, user, role, or user group to audit or manage endpoints.

Instructions

Retrieve paired mobile devices (Zabbix 8.0+): the Zabbix mobile app installations that users onboarded, with the owning userid, device name, status, activated_at and lastaccess. Filter by deviceids, userids, roleids or usrgrpids. Use device_offboard to revoke a device.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of records to return.
filterNoReturn only results whose properties exactly match the given values (a single value or a list of values per key). Example: {"status": 0} or {"status": [0, 1]}. Keys: activated_at, deviceid, lastaccess, name, status, userid, uuid. Text properties cannot be filtered; use 'search' for them.
outputNoProperties of the device object to return. Pass 'extend' for all, 'count' for the number of matches only, or a comma-separated list of property names. Default when omitted: deviceid, userid, name, status, lastaccess. Properties: activated_at, deviceid, lastaccess, name, status, userid, uuid.
searchNoReturn results whose string properties contain the given pattern (case-insensitive; '*' is a wildcard when searchWildcardsEnabled is true). Example: {"name": "web"}. Keys: name, uuid.
serverNoTarget Zabbix server. Available: default. Defaults to 'default' if omitted.
roleidsNoReturn only devices belonging to users with the given roles.
useridsNoReturn only devices belonging to the given users.
raw_jsonNoStrips the security disclaimer preamble from the response so it is pure JSON. Default: false. Requires the bearer token to have 'allow_raw_json' explicitly enabled by an operator in the admin portal - tokens without that policy receive a PolicyError instead. WARNING: setting true bypasses the prompt-injection mitigation marker that wraps untrusted Zabbix data (host names, item descriptions, problem text). LLM clients (Claude, GPT, Cursor, ...) should leave this false; only programmatic non-LLM consumers (Python scripts, n8n workflows that json.loads the result) should set true.
deviceidsNoReturn only devices with the given IDs.
sortfieldNoSort by one or more of: deviceid, name (comma-separated for several; pair with 'sortorder'). No other property is sortable.
sortorderNoSort order: 'ASC' or 'DESC'.
usrgrpidsNoReturn only devices belonging to users in the given user groups.
countOutputNoReturn the count of matching devices instead of the records.
extra_paramsNoOther native device.get parameters, merged into the request as-is. device.get has no parameters beyond the typed ones. Any other key is refused here, because Zabbix would silently ignore it. For a parameter you are sure exists on your release but is not listed, use zabbix_raw_api_call.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.41.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds value beyond them: the Zabbix 8.0+ availability gate, the precise definition of the returned entity, the default property set, and the sibling that performs revocation. It does not discuss pagination behavior or permission requirements, which keeps it from a 5.

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

Conciseness5/5

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

Three compact sentences, front-loaded with purpose and entity definition, then filters, then the alternative tool. No filler, and the routing cue is placed last where an agent deciding between read and revoke will see it.

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

Completeness5/5

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

For a 14-parameter, zero-required read tool with an output schema present, the description covers purpose, entity definition, version gate, filterable dimensions, and the destructive sibling. Return values need not be explained because the output schema exists, so nothing essential is missing.

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 100%, so every parameter (filter, search, output, sortfield, raw_json, etc.) is already fully documented in the schema. The description restates the filter keys and the default returned properties, which is mild reinforcement rather than added meaning. Baseline 3 applies 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.

Purpose5/5

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

States a specific verb and resource ('Retrieve paired mobile devices') and immediately defines what a device actually is ('the Zabbix mobile app installations that users onboarded'), plus the fields returned. The Zabbix 8.0+ version qualifier and the device_offboard pointer let an agent distinguish this from sibling *_get tools without opening the schema.

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?

Gives clear context for when to reach for this tool (paired mobile devices, filtered by deviceids/userids/roleids/usrgrpids) and routes the destructive counterpart to device_offboard. It stops short of stating when this tool is the wrong choice versus other user/audit listing tools, so it is clear but not fully exclusionary.

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