Skip to main content
Glama
Sign In
Zabbix MCP Server

Zabbix MCP Server

by initMAX
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

housekeeping_get

Read-only

Retrieve global housekeeping settings to review automatic cleanup periods for history, trends, events, alerts, sessions, and audit logs.

Instructions

Get housekeeping settings. Returns the global configuration that controls automatic cleanup of old data: history storage period, trend storage period, event and alert retention, session cleanup interval, and audit log retention. This is a singleton object.

Input Schema

NameRequiredDescriptionDefault
outputNoProperties of the housekeeping object to return. Pass 'extend' for all, or a list of property names. Default when omitted: 'extend'. Properties: compress_older, compression_status, db_extension, hk_audit, hk_audit_mode, hk_events_autoreg, hk_events_discovery, hk_events_internal, hk_events_mode, hk_events_service (6.0+), hk_events_trigger, hk_history, hk_history_global, hk_history_mode, hk_services, hk_services_mode, hk_sessions, hk_sessions_mode, hk_trends, hk_trends_global, hk_trends_mode.
serverNoTarget Zabbix server. Available: default. Defaults to 'default' if omitted.
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.
extra_paramsNoOther native housekeeping.get parameters, merged into the request as-is. housekeeping.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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.42.2
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / extra_params / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / output / anyOf
      Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "extend"
+    ],
+    "type": "string"
+  },
+  {
+    "items": {
+      "enum": [
+        "compress_older",
+        "compression_status",
+        "db_extension",
+        "hk_audit",
+        "hk_audit_mode",
+        "hk_events_autoreg",
+        "hk_events_discovery",
+        "hk_events_internal",
+        "hk_events_mode",
+        "hk_events_service",
+        "hk_events_trigger",
+        "hk_history",
+        "hk_history_global",
+        "hk_history_mode",
+        "hk_services",
+        "hk_services_mode",
+        "hk_sessions",
+        "hk_sessions_mode",
+        "hk_trends",
+        "hk_trends_global",
+        "hk_trends_mode"
+      ],
+      "type": "string"
+    },
+    "minItems": 1,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / output / description
      Previous value: -"Properties of the housekeeping 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: compress_older, compression_status, db_extension, hk_audit, hk_audit_mode, hk_events_autoreg, hk_events_discovery, hk_events_internal, hk_events_mode, hk_events_service (6.0+), hk_events_trigger, hk_history, hk_history_global, hk_history_mode, hk_services, hk_services_mode, hk_sessions, hk_sessions_mode, hk_trends, hk_trends_global, hk_trends_mode."New value: +"Properties of the housekeeping object to return. Pass 'extend' for all, or a list of property names. Default when omitted: 'extend'. Properties: compress_older, compression_status, db_extension, hk_audit, hk_audit_mode, hk_events_autoreg, hk_events_discovery, hk_events_internal, hk_events_mode, hk_events_service (6.0+), hk_events_trigger, hk_history, hk_history_global, hk_history_mode, hk_services, hk_services_mode, hk_sessions, hk_sessions_mode, hk_trends, hk_trends_global, hk_trends_mode."
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "result": {
-      "title": "Result",
-      "type": "string"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "title": "housekeeping_getOutput",
-  "type": "object"
-}New value: +null
  2. First observedv1.41.0

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=false, so the safety profile is covered and the bar is lower. The description contributes the useful fact that the result is a single global object rather than a collection, but says nothing about permissions, whether values reflect the frontend or server config, or version-dependent fields. The richer behavior detail (raw_json policy gating, injection-marker stripping) lives in the schema, not the description.

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?

Three short sentences, zero filler, with the core purpose front-loaded and the retention topics listed immediately after. Nothing is repeated from the schema or annotations.

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 parameterless read of a singleton config object with no output schema, enumerating the returned fields in the description is the right compensating move and it does so. Minor gap: it does not note that some fields (e.g. hk_events_service) are version-gated, even though the schema does.

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% and each of the four parameters carries a detailed description, including the raw_json policy requirement and extra_params escape hatch to zabbix_raw_api_call. The description adds no parameter meaning of its own, so baseline 3 applies — the schema is doing all of that work.

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?

States a specific verb and resource (get housekeeping settings) and enumerates what the resource governs — history/trend storage periods, event and alert retention, session cleanup, audit log retention. It also discloses the shape of the object ('singleton'). It stops short of distinguishing itself from the near-neighbor settings_get, which an agent could easily confuse with it.

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?

Usage is only implied: an agent can infer this is the read path for cleanup/retention configuration, but the description never says when to prefer it over settings_get or zabbix_raw_api_call, nor that no write counterpart exists in the sibling list. No exclusions or preconditions are stated.

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

Deploy Server

Other Tools