Zabbix MCP Server

Overview Schema Source Related Servers Discussions Admin

trend_get

Read-only

Retrieve hourly aggregated min/avg/max trend data to analyze long-term metric behavior and reduce data volume. Filter by item IDs and time range.

Instructions

Retrieve trend data (hourly aggregated min/avg/max values). Trends are calculated from history and provide a compact, long-term view of metric behaviour. Each record covers a one-hour period and includes the minimum, average, and maximum values as well as the number of values collected. Use trends instead of history for time ranges spanning days or more to reduce data volume. Filter by 'itemids' and use 'time_from' / 'time_till' to bound the time range.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of results to return.
`output`	No	Properties of the trend 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: 'extend'. Properties: clock, itemid, num, value_avg, value_max, value_min.
`server`	No	Target Zabbix server. Available: default. Defaults to 'default' if omitted.
`itemids`	No	Return only trend data for the given item 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.
`time_from`	No	Return only trend data 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_till`	No	Return only trend data 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.
`extra_params`	No	Other native trend.get parameters, merged into the request as-is. trend.get has no parameters beyond the typed ones. 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.

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

A4.4/5.0

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 adds genuine domain context beyond that: trends are derived from history, each record covers a one-hour bucket with min/avg/max plus sample count, and the aggregation exists to reduce data volume. It omits pagination/limit behaviour and result ordering, which are minor given the read-only annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five tight sentences: what the tool returns, how trends are computed, record shape, the routing rule versus history, and the filter parameters. Purpose and the sibling distinction are front-loaded with no filler.

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?

An output schema exists, so return-value explanation is not required. The description covers purpose, aggregation semantics, usage routing and filters, which is sufficient for a 9-parameter read tool; only marginal items like limit/pagination behaviour are left 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 the baseline is 3. The description names itemids, time_from and time_till as the key filters, but adds no syntax, format, or default detail beyond what the schema already documents for those parameters.

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 trend data (hourly aggregated min/avg/max values)' states a specific verb and resource, and the description immediately contrasts the resource with history ('Use trends instead of history'), letting an agent distinguish it from the history_get sibling without opening 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 (history) and the condition that selects this tool ('for time ranges spanning days or more to reduce data volume'), plus the filtering approach ('Filter by itemids and use time_from/time_till'). This is exactly the routing guidance the calibration's highest-scoring example rewarded.

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

Deploy Server