Zabbix MCP Server

Overview Schema Source Related Servers Discussions Admin

alert_get

Read-only

Retrieve Zabbix alert log entries to diagnose failed notifications, view delivery status, retry counts, error messages, and message bodies. Filter by time window to pinpoint delivery issues.

Instructions

Retrieve the alert log -- a read-only record of every notification and remote command Zabbix has executed as a result of actions. Each alert entry contains delivery status, retry count, error text (if failed), and the message body. Use time_from/time_till to scope by time window. Great for diagnosing 'why didn't I get notified?' issues.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of results to return.
`filter`	No	Return 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: acknowledgeid, actionid, alertid, alerttype, clock, error, esc_step, eventid, mediatypeid, p_eventid, retries, sendto, status, subject, userid. Text properties cannot be filtered; use 'search' for them.
`output`	No	Properties of the alert 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: alertid, actionid, mediatypeid, status, clock. Properties: acknowledgeid, actionid, alertid, alerttype, clock, error, esc_step, eventid, mediatypeid, message, p_eventid, retries, sendto, status, subject, userid.
`search`	No	Return results whose string properties contain the given pattern (case-insensitive; '*' is a wildcard when searchWildcardsEnabled is true). Example: {"name": "web"}. Keys: error, message, sendto, subject.
`server`	No	Target Zabbix server. Available: default. Defaults to 'default' if omitted.
`hostids`	No	Return only alerts for the given host IDs.
`alertids`	No	Return only alerts with the given IDs.
`groupids`	No	Return only alerts for hosts belonging to these host group IDs.
`raw_json`	No	Strips 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.
`actionids`	No	Return only alerts generated by the given action IDs.
`sortfield`	No	Sort by one or more of: alertid, clock, eventid, mediatypeid, sendto, status (comma-separated for several; pair with 'sortorder'). No other property is sortable.
`sortorder`	No	Sort order: 'ASC' (ascending) or 'DESC' (descending).
`time_from`	No	Return only alerts 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). Useful for auditing recent notification delivery.
`time_till`	No	Return only alerts 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).
`countOutput`	No	Return the count of matching results instead of the actual data.
`searchByAny`	No	If true, return results matching ANY search field (OR). Default is ALL fields (AND).
`extra_params`	No	Other native alert.get parameters, merged into the request as-is. Parameters: eventids, eventobject, eventsource, mediatypeids, objectids, userids. Sub-object selects (value 'extend', 'count' or a list of property names): selectHosts, selectMediatypes, selectUsers. 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.
`searchWildcardsEnabled`	No	If true, enable * and ? wildcards in search patterns.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.41.0Oct 20, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description needn't restate safety. It usefully adds the semantics of the returned entries (delivery status, retry count, error text, message body), but says nothing about auth needs, result volume, or pagination behavior beyond 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?

It is front-loaded: the identity and contents of the alert log come first, then scoping advice, then the diagnostic use case. Three sentences, each doing work, though the closing 'Great for diagnosing...' sentence is slightly promotional rather than strictly informational.

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?

With an output schema present, the description need not explain return values, and annotations cover the safety profile. For an 18-parameter read tool it covers purpose, scoping, and a motivating use case adequately; only explicit sibling routing 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% across all 18 parameters, including detailed notes on filter/search/output/raw_json, so the schema carries the parameter burden. The description only calls out time_from/time_till scoping, adding no syntax or format detail beyond what the schema already provides. 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?

The description states a concrete verb and resource ('Retrieve the alert log') and defines the resource precisely as 'a read-only record of every notification and remote command Zabbix has executed as a result of actions.' This definition implicitly separates it from siblings like event_get and auditlog_get, but no sibling is named explicitly, so it stops short of a 5.

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 gives a clear use case ('diagnosing why didn't I get notified?') and points at the time_from/time_till parameters for scoping. However, it never says when NOT to use it or names an alternative such as event_get or auditlog_get, so there is no routing guidance for ambiguous cases.

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

Deploy Server