Skip to main content
Glama
initMAX

Zabbix MCP Server

event_get

Read-only

Retrieve complete Zabbix event history, including resolved and PROBLEM/OK events, to audit state changes and correlate trigger, discovery, or autoregistration activity.

Instructions

Retrieve events generated by triggers, discovery rules, or autoregistration. Events form the full audit trail of state changes. For active/current problems only, prefer problem.get instead. Use event.get when you need the complete event history including resolved events, or when you need to correlate PROBLEM and OK events. Filter by 'source' (0=trigger, 1=discovery, 2=autoregistration, 3=internal) and 'object' to narrow results. Use 'time_from'/'time_till' for time-bounded queries and 'severity_min' to filter by importance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of results to return.
valueNoEvent value filter: 0=OK (resolved), 1=PROBLEM (active).
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: acknowledged, cause_eventid (6.4+), cep_ruleid (8.0+), clock, eventid, flags (8.0+), name, ns, object, objectid, severity, source, value. Text properties cannot be filtered; use 'search' for them.
objectNoEvent object type: 0=trigger, 1=discovered host, 2=discovered service, 3=autoregistration event, 4=item, 5=LLD rule.
outputNoProperties of the event 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: eventid, name, severity, clock, value, r_eventid. Properties: acknowledged, c_eventid, cause_eventid (6.4+), cep_ruleid (8.0+), clock, correlationid, eventid, flags (8.0+), name, ns, object, objectid, opdata, r_eventid, severity, source, suppressed, urls, userid, value.
searchNoReturn results whose string properties contain the given pattern (case-insensitive; '*' is a wildcard when searchWildcardsEnabled is true). Example: {"name": "web"}. Keys: name.
serverNoTarget Zabbix server. Available: default. Defaults to 'default' if omitted.
sourceNoEvent source: 0=trigger (default), 1=discovery, 2=autoregistration, 3=internal.
hostidsNoReturn only events for the given hosts.
eventidsNoReturn only events with the given IDs.
groupidsNoReturn only events for hosts belonging to the given host groups.
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.
objectidsNoReturn only events for the given trigger/item/LLD rule IDs (depends on the 'object' parameter).
sortfieldNoSort by one or more of: eventid, objectid, clock (comma-separated for several; pair with 'sortorder'). No other property is sortable.
sortorderNoSort order: 'ASC' (ascending) or 'DESC' (descending).
time_fromNoReturn only events generated after this time (Unix timestamp, ISO 8601 date-time such as 2026-04-01T08:00:00Z, or a relative time such as now-1h, now/d or now-7d/d; a value without a zone is read in the zone resolved for the call) (inclusive).
time_tillNoReturn only events generated before this time (Unix timestamp, ISO 8601 date-time such as 2026-04-01T08:00:00Z, or a relative time such as now-1h, now/d or now-7d/d; a value without a zone is read in the zone resolved for the call) (inclusive).
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).
acknowledgedNoIf true, return only acknowledged events. If false, only unacknowledged events.
extra_paramsNoOther native event.get parameters, merged into the request as-is. Parameters: action (7.0+), action_userids (7.0+), evaltype, eventid_from, eventid_till, groupBy (7.0+), problem_time_from, problem_time_till, severities, suppressed, symptom (6.4+), tags, trigger_severities (7.0+). Sub-object selects (value 'extend', 'count' or a list of property names): selectAcknowledges (7.0+), selectAlerts (7.0+), selectHosts, selectRelatedObject, selectSuppressionData, selectTags, select_acknowledges (removed in 7.2), select_alerts (removed in 7.2). 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.
severity_minNoReturn only events with severity greater than or equal to this value: 0=not classified, 1=information, 2=warning, 3=average, 4=high, 5=disaster.
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

A4.3/5.0
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 still adds real context: that this returns the full audit trail including resolved events rather than just current state, which goes beyond the safety hints. It stops short of disclosing pagination or output shape, but an output schema exists and the additional scope framing justifies a 4.

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-loads purpose, then the alternative and the selection rationale, then the main filters — a sensible order. Slight redundancy in re-listing the source codes already present in the schema keeps it from a 5.

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 23-parameter tool with an output schema and annotations, the description covers purpose, routing, and the primary filter axes an agent needs. Output shape need not be explained given the output schema exists; only advanced parameters like raw_json are left entirely to the schema.

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 the source/object code tables and time formats is already documented in the schema. The description restates the 'source' and 'severity_min' enumerations (e.g. 0=trigger, 1=discovery) rather than adding meaning beyond them. Baseline 3 is appropriate.

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?

The opening states a specific verb and resource ('Retrieve events generated by triggers, discovery rules, or autoregistration') and frames the result as 'the full audit trail of state changes'. It explicitly differentiates itself from the closest sibling, problem.get, so an agent can tell them apart without reading either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names the alternative ('prefer problem.get instead') and the precise condition that selects this tool ('complete event history including resolved events', 'correlate PROBLEM and OK events'). Both the when-to-use and when-not-to-use are explicit.

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