Skip to main content
Glama
Zabbix MCP Server

Zabbix MCP Server

dhost_get

Read-only

Retrieve read-only Zabbix discovered hosts found by network discovery rules, filtered by rule, status, or ID, to inspect discovery results and associated services.

Instructions

Retrieve discovered hosts (read-only). Discovered hosts are hosts found by network discovery rules. Each discovered host may have one or more discovered services (dservice) representing the checks that succeeded.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of results 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: dhostid, druleid, lastdown, lastup, status. Text properties cannot be filtered; use 'search' for them.
outputNoProperties of the dhost object to return. Pass 'extend' for all, 'count' for the number of matches only, or a list of property names. Default when omitted: dhostid, druleid, status. Properties: dhostid, druleid, lastdown, lastup, status.
searchNoReturn results that match the given pattern (case-insensitive by default). Example: {"name": "web"} finds 'Web Server', 'my-web-app', etc.
serverNoTarget Zabbix server. Available: default. Defaults to 'default' if omitted.
dhostidsNoReturn only discovered hosts with the given IDs.
druleidsNoReturn only discovered hosts found by the given network discovery rules.
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.
sortfieldNoSort by one or more of: dhostid, druleid (a list for several; pair with 'sortorder'). No other property is sortable.
sortorderNoSort order: 'ASC' (ascending) or 'DESC' (descending).
countOutputNoReturn the count of matching results instead of the actual data.
searchByAnyNoIf true, return results matching ANY search field (OR). Default is ALL fields (AND).
extra_paramsNoOther native dhost.get parameters, merged into the request as-is. Parameters: dserviceids, groupCount, limitSelects. Switches (true turns one on, false is the same as leaving it out): groupCount. groupCount goes with output='count': the count is then split by the ID filters the method groups by (hostids, groupids ...), one row per ID with 'rowscount'; a single row without such a filter. Sub-object selects (value 'extend', 'count' or a list of property names): selectDRules, selectDServices. 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.
searchWildcardsEnabledNoIf true, enable * and ? wildcards in search patterns.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv1.42.2
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / extra_params / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "propertyNames": {
      +      "enum": [
      +        "editable",
      +        "excludeSearch",
      +        "preservekeys",
      +        "startSearch",
      +        "dserviceids",
      +        "groupCount",
      +        "limitSelects",
      +        "selectDRules",
      +        "selectDServices"
      +      ]
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / extra_params / description
      Previous value: -"Other native dhost.get parameters, merged into the request as-is. Parameters: dserviceids, limitSelects. Sub-object selects (value 'extend', 'count' or a list of property names): selectDRules, selectDServices. 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."New value: +"Other native dhost.get parameters, merged into the request as-is. Parameters: dserviceids, groupCount, limitSelects. Switches (true turns one on, false is the same as leaving it out): groupCount. groupCount goes with output='count': the count is then split by the ID filters the method groups by (hostids, groupids ...), one row per ID with 'rowscount'; a single row without such a filter. Sub-object selects (value 'extend', 'count' or a list of property names): selectDRules, selectDServices. 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."
    • changedInput schema / properties / filter / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "propertyNames": {
      +      "enum": [
      +        "dhostid",
      +        "druleid",
      +        "lastdown",
      +        "lastup",
      +        "status"
      +      ]
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / output / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "extend",
      +      "count"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "enum": [
      +        "dhostid",
      +        "druleid",
      +        "lastdown",
      +        "lastup",
      +        "status"
      +      ],
      +      "type": "string"
      +    },
      +    "minItems": 1,
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / output / description
      Previous value: -"Properties of the dhost 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: dhostid, druleid, status. Properties: dhostid, druleid, lastdown, lastup, status."New value: +"Properties of the dhost object to return. Pass 'extend' for all, 'count' for the number of matches only, or a list of property names. Default when omitted: dhostid, druleid, status. Properties: dhostid, druleid, lastdown, lastup, status."
    • changedInput schema / properties / sortfield / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "dhostid",
      +      "druleid"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "enum": [
      +        "dhostid",
      +        "druleid"
      +      ],
      +      "type": "string"
      +    },
      +    "minItems": 1,
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / sortfield / description
      Previous value: -"Sort by one or more of: dhostid, druleid (comma-separated for several; pair with 'sortorder'). No other property is sortable."New value: +"Sort by one or more of: dhostid, druleid (a list for several; pair with 'sortorder'). No other property is sortable."
    • changedInput schema / properties / sortorder / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "ASC",
      +      "DESC"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "enum": [
      +        "ASC",
      +        "DESC"
      +      ],
      +      "type": "string"
      +    },
      +    "minItems": 1,
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "result": {
      -      "title": "Result",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "result"
      -  ],
      -  "title": "dhost_getOutput",
      -  "type": "object"
      -}New value: +null
  2. First observedv1.41.0

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 and openWorldHint=false, so the description's '(read-only)' adds nothing beyond structured data. What it does add is domain context: discovered hosts originate from discovery rules and are parent objects to discovered services. It says nothing about result set size, pagination via limit, or default output fields — though much of that lives in the schema.

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 and resource. The parenthetical '(read-only)' is mildly redundant with the annotations, but there is no filler otherwise.

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?

For a 14-parameter tool with no output schema, the description is thin — it never mentions that results are returned as dhost property objects, that 'count' is available, or how it relates to dservice_get. It is offset by an exceptionally rich input schema, so the definition is workable but not self-sufficient.

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% and each of the 14 parameters is documented in detail (filter keys, output options, raw_json security caveat, extra_params allow-list). The description contributes no parameter meaning at all, 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?

States a specific verb and resource ('Retrieve discovered hosts') and defines what a discovered host actually is — a host found by a network discovery rule — which is not inferable from the name alone. It does not explicitly contrast itself with near siblings such as host_get, drule_get, or dservice_get, so differentiation is left to the reader.

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. Given siblings like host_get (configured hosts), drule_get (discovery rules), and dservice_get (services on these hosts), a sentence saying 'use dservice_get to list the services of a discovered host' would have removed real ambiguity. The description only defines the concept, leaving tool selection to inference.

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