Skip to main content
Glama
Zabbix MCP Server

Zabbix MCP Server

service_get

Read-only

Retrieve Zabbix business services, computed statuses, and parent/child trees; filter by IDs, tags, problem tags, or SLAs to inspect service health and dependencies.

Instructions

Retrieve business services: the service tree whose status is computed from problems matched by problem tags and propagated along parent / child links (algorithm, weight, propagation_rule), with SLAs attached via service tags. Filter by serviceids, parentids (deep_parentids=true for the whole subtree), childids, tags, problem_tags or slaids. Use selectParents, selectChildren, selectTags, selectProblemTags, selectProblemEvents, selectStatusRules and selectStatusTimeline in extra_params to include related data. Before Zabbix 6.0 services were trigger-based (triggerid, goodsla, showsla) and the SLA lived here; since 6.0 the SLA is sla_get / sla_getsli.

Input Schema

NameRequiredDescriptionDefault
tagsNoReturn only services with the given tags: [{'tag': ..., 'value': ..., 'operator': ...}] (6.0+).
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: algorithm, created_at (6.0+), description (6.0+), name, propagation_rule (6.0+), propagation_value (6.0+), readonly (6.0+), serviceid, sortorder, status, uuid (6.0+), weight (6.0+). Text properties cannot be filtered; use 'search' for them.
outputNoProperties of the service object to return. Pass 'extend' for all, 'count' for the number of matches only, or a list of property names. Default when omitted: serviceid, name, status, algorithm, sortorder. Properties: algorithm, created_at (6.0+), description (6.0+), name, propagation_rule (6.0+), propagation_value (6.0+), readonly (6.0+), serviceid, sortorder, status, uuid (6.0+), weight (6.0+).
searchNoReturn results whose string properties contain the given pattern (case-insensitive; '*' is a wildcard when searchWildcardsEnabled is true). Example: {"name": "web"}. Keys: description (6.0+), name, uuid (6.0+).
serverNoTarget Zabbix server. Available: default. Defaults to 'default' if omitted.
slaidsNoReturn only services covered by the given SLAs (6.0+).
childidsNoReturn only parents of the given services.
evaltypeNoHow tag conditions combine: 0 = And/Or (default), 2 = Or (6.0+).
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.
parentidsNoReturn only children of the given services (direct, or the whole subtree with deep_parentids).
sortfieldNoSort by one or more of: created_at (6.0+), name, serviceid (6.0+), sortorder, status (6.0+) (a list for several; pair with 'sortorder'). No other property is sortable.
sortorderNoSort order: 'ASC' (ascending) or 'DESC' (descending).
serviceidsNoReturn only services with the given IDs.
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 service.get parameters, merged into the request as-is. Sub-object selects (value 'extend', 'count' or a list of property names): selectChildren (6.0+), selectParents (6.0+), selectProblemEvents (6.0+), selectProblemTags (6.0+), selectStatusRules (6.0+), selectStatusTimeline (6.0+), selectTags (6.0+). 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.
problem_tagsNoReturn only services whose problem tags match: [{'tag': ..., 'value': ..., 'operator': ...}] (6.0+).
deep_parentidsNoWith parentids: return every descendant, not only direct children (6.0+).
without_problem_tagsNoReturn only services that have no problem tags (6.0+).
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",
      +        "selectChildren",
      +        "selectParents",
      +        "selectProblemEvents",
      +        "selectProblemTags",
      +        "selectStatusRules",
      +        "selectStatusTimeline",
      +        "selectTags",
      +        "selectAlarms",
      +        "selectDependencies",
      +        "selectParent",
      +        "selectParentDependencies",
      +        "selectTimes",
      +        "selectTrigger"
      +      ]
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / filter / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "propertyNames": {
      +      "enum": [
      +        "algorithm",
      +        "created_at",
      +        "description",
      +        "name",
      +        "propagation_rule",
      +        "propagation_value",
      +        "readonly",
      +        "serviceid",
      +        "sortorder",
      +        "status",
      +        "uuid",
      +        "weight",
      +        "goodsla",
      +        "showsla",
      +        "triggerid"
      +      ]
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / output / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "extend",
      +      "count"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "enum": [
      +        "algorithm",
      +        "created_at",
      +        "description",
      +        "name",
      +        "propagation_rule",
      +        "propagation_value",
      +        "readonly",
      +        "serviceid",
      +        "sortorder",
      +        "status",
      +        "uuid",
      +        "weight",
      +        "goodsla",
      +        "showsla",
      +        "triggerid"
      +      ],
      +      "type": "string"
      +    },
      +    "minItems": 1,
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / output / description
      Previous value: -"Properties of the service 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: serviceid, name, status, algorithm, sortorder. Properties: algorithm, created_at (6.0+), description (6.0+), name, propagation_rule (6.0+), propagation_value (6.0+), readonly (6.0+), serviceid, sortorder, status, uuid (6.0+), weight (6.0+)."New value: +"Properties of the service object to return. Pass 'extend' for all, 'count' for the number of matches only, or a list of property names. Default when omitted: serviceid, name, status, algorithm, sortorder. Properties: algorithm, created_at (6.0+), description (6.0+), name, propagation_rule (6.0+), propagation_value (6.0+), readonly (6.0+), serviceid, sortorder, status, uuid (6.0+), weight (6.0+)."
    • changedInput schema / properties / search / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": true,
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "propertyNames": {
      +      "enum": [
      +        "description",
      +        "name",
      +        "uuid",
      +        "triggerid"
      +      ]
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / sortfield / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "created_at",
      +      "name",
      +      "serviceid",
      +      "sortorder",
      +      "status"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "enum": [
      +        "created_at",
      +        "name",
      +        "serviceid",
      +        "sortorder",
      +        "status"
      +      ],
      +      "type": "string"
      +    },
      +    "minItems": 1,
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / sortfield / description
      Previous value: -"Sort by one or more of: created_at (6.0+), name, serviceid (6.0+), sortorder, status (6.0+) (comma-separated for several; pair with 'sortorder'). No other property is sortable."New value: +"Sort by one or more of: created_at (6.0+), name, serviceid (6.0+), sortorder, status (6.0+) (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": "service_getOutput",
      -  "type": "object"
      -}New value: +null
  2. First observedv1.41.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare a safe read, so the remaining burden is domain behavior, and the description supplies the important part: status is computed, not stored, from problem tags propagated via algorithm/weight/propagation_rule, and SLA attachment is version-dependent. It adds that unrecognized extra_params keys are refused rather than silently ignored, which is useful non-obvious behavior. It does not characterize result size or pagination behavior with no limit given.

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?

Purpose is front-loaded in the first clause and the sentences are dense but purposeful, with no filler. It is on the long side and the version-compatibility clause at the end packs several facts into one sentence, but nothing is wasted.

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

Completeness4/5

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

For a 21-parameter, zero-required tool with no output schema, the description covers the resource semantics, the filter axes, the selectable sub-objects, and the Zabbix version split that changes what an SLA field even means. What is missing is modest: default result size or behavior when no filter is supplied, though the schema does document the default output projection.

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 the schema already documents every parameter, and the description mostly restates the filter set and the extra_params select list. The one genuinely additive bit is the parentids/deep_parentids relationship and the childids inversion, but the schema already states both. Baseline 3 applies.

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?

'Retrieve business services' plus an explicit model of what a service is (a tree whose status is computed from problem tags and propagated along parent/child links) goes far beyond naming the resource. It also explicitly separates the SLA concern ('since 6.0 the SLA is sla_get / sla_getsli'), which keeps it distinct from the similar-looking sla_get sibling.

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?

It tells the agent which filters select which services (serviceids, parentids with deep_parentids, childids, tags, problem_tags, slaids) and routes SLA retrieval to sla_get / sla_getsli. It also routes unknown parameters to zabbix_raw_api_call. It stops short of stating when not to use this tool (e.g., preferring a host/problem tool for non-service data), so it is not a full when/when-not treatment.

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