Skip to main content
Glama
initMAX

Zabbix MCP Server

service_get

Read-only

Retrieve Zabbix business services and their computed status trees, filtered by IDs, tags, problem tags, or SLAs, with optional parent, child, and event details.

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

TableJSON 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 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+).
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+) (comma-separated 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.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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 cover the safe-read profile (readOnlyHint=true) and open-world scope. The description adds substantive domain behavior beyond that: how status is computed from problem tags and propagated, and the version-dependent model change at 6.0. It does not touch rate limits or pagination behavior, keeping it out of the top band.

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 sentences, all front-loaded with the highest-value information (what it is, how to filter, version caveat). The first sentence is dense but every clause carries domain meaning; nothing is padding.

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 tool with an output schema present, the description covers the conceptual model, filter set, related-data selectors and version migration — the things the schema cannot convey. A little more on the additional filter flags (evaltype, without_problem_tags) would round it out, but the essentials are all there.

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 (including raw_json and extra_params) is already documented in the schema. The description restates the filter list and names the extra_params selectors, adding mild emphasis but no syntax or format detail beyond the schema — the expected baseline of 3.

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 business services: the service tree') and immediately explains the domain model — status computed from problem tags and propagated along parent/child links. It explicitly differentiates itself from the sla_get/sla_getsli siblings for post-6.0 SLA data, so an agent can route correctly without opening any 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?

Provides clear routing guidance: SLAs live in sla_get/sla_getsli since 6.0, while trigger-based goodsla/triggerid applied pre-6.0. It also lists which filters/selects to reach for. No explicit when-not-to-use beyond the SLA redirect, so not a full 5.

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