Zabbix MCP Server

Overview Schema Source Related Servers Discussions Admin

image_get

Read-only

Retrieve images stored in Zabbix for map icons and backgrounds, returning base64 data or metadata; filter, search, sort, or limit by image ID, name, or type.

Instructions

Retrieve images stored in Zabbix. Images are used as icons for map elements and as backgrounds for network maps. Two types exist: 1 = icon, 2 = background. By default the image data (base64-encoded) is included in the response; use 'output' to limit returned fields if you only need metadata.

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: imageid, imagetype, name. Text properties cannot be filtered; use 'search' for them.
`output`	No	Properties of the image 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: imageid, name, imagetype. Properties: image (6.4+), imageid, imagetype, name.
`search`	No	Return results whose string properties contain the given pattern (case-insensitive; '*' is a wildcard when searchWildcardsEnabled is true). Example: {"name": "web"}. Keys: name.
`server`	No	Target Zabbix server. Available: default. Defaults to 'default' if omitted.
`imageids`	No	Return only images with the given 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.
`sortfield`	No	Sort by one or more of: imageid, name (comma-separated for several; pair with 'sortorder'). No other property is sortable.
`sortorder`	No	Sort order: 'ASC' (ascending) or 'DESC' (descending).
`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 image.get parameters, merged into the request as-is. Parameters: sysmapids. Sub-object selects (value 'extend', 'count' or a list of property names): select_image. 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

A3.9/5.0

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 behavioral context beyond them: the response includes base64-encoded image data by default, which implies a heavy payload, and it explains the two enumerable image types. It stops short of noting auth or pagination behavior.

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 front-loaded sentences: purpose, domain context, then the output nuance. Nothing is padded, though the map-background detail is slightly peripheral.

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, return values need not be documented, and all 13 parameters are fully described in the schema. The description covers the essentials; only the default-output framing could use reconciliation with 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 coverage is 100%, so the baseline is 3. The description adds one useful semantic ('1 = icon, 2 = background') that the schema's imagetype filter lacks, but its claim that image data is included by default sits awkwardly against the schema's stated default output (imageid, name, imagetype, which omits the image property).

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 images stored in Zabbix') and immediately explains what images are for (map icons, map backgrounds). No sibling tool retrieves images, so it is unambiguously differentiated from the surrounding *_get family.

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

Usage Guidelines3/5

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

The description gives one implied usage condition ('use output to limit returned fields if you only need metadata') but never states when to choose this over alternatives or any prerequisite. Usage is inferable but not spelled out.

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

Deploy Server