Skip to main content
Glama
initMAX

Zabbix MCP Server

dservice_get

Read-only

Retrieve read-only discovered services from Zabbix, filtering by discovery rule, host, IP, port, or status to inspect which checks responded during network discovery.

Instructions

Retrieve discovered services (read-only). Discovered services represent individual checks (ports, protocols) that responded on a discovered host. They belong to discovered hosts (dhost) and are created by network discovery rules (drule).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of results to return.
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: dcheckid, dhostid, dns, dserviceid, ip, lastdown, lastup, port, status, value. Text properties cannot be filtered; use 'search' for them.
outputNoProperties of the dservice 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: dserviceid, dhostid, dcheckid, ip, port, status. Properties: dcheckid, dhostid, dns, dserviceid, ip, lastdown, lastup, port, status, value.
searchNoReturn results whose string properties contain the given pattern (case-insensitive; '*' is a wildcard when searchWildcardsEnabled is true). Example: {"name": "web"}. Keys: dns, ip, value.
serverNoTarget Zabbix server. Available: default. Defaults to 'default' if omitted.
dhostidsNoReturn only discovered services belonging to the given discovered hosts.
druleidsNoReturn only discovered services found by the given network discovery rules.
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.
sortfieldNoSort by one or more of: dserviceid, dhostid, ip (comma-separated for several; pair with 'sortorder'). No other property is sortable.
sortorderNoSort order: 'ASC' (ascending) or 'DESC' (descending).
countOutputNoReturn the count of matching results instead of the actual data.
dserviceidsNoReturn only discovered services with the given IDs.
searchByAnyNoIf true, return results matching ANY search field (OR). Default is ALL fields (AND).
extra_paramsNoOther native dservice.get parameters, merged into the request as-is. Parameters: dcheckids, limitSelects. Sub-object selects (value 'extend', 'count' or a list of property names): selectDHosts, selectDRules, selectHosts. 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.
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

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, and the description's '(read-only)' merely restates that rather than adding new behavioral information. It does contribute model context (dservice are created by discovery rules, belong to discovered hosts), but says nothing about pagination, default limits, or result volume. With annotations covering the safety profile, this is adequate but thin.

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 short sentences, front-loaded with the action and scoped immediately by '(read-only)', followed by the domain model. Every sentence carries meaning and there is no filler. Minor deduction because '(read-only)' duplicates the readOnlyHint annotation instead of adding fresh information.

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 unnecessary, and the input schema exhaustively documents all 15 parameters including the risky raw_json flag. For a read-only collection-getter in a large sibling family, the description supplies the needed object semantics; only an explicit sibling routing hint 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%  all 15 parameters (filter, output, search, dhostids, druleids, raw_json, sortfield, etc.) are documented in-schema with examples and constrained key lists. The description adds no parameter-level detail beyond the domain framing, so the baseline of 3 applies; the schema is doing all the 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 ('Retrieve discovered services') and then defines the domain object precisely: individual port/protocol checks that responded on a discovered host. This lets an agent distinguish dservices from dhost_get (hosts) and dcheck_get (check definitions) conceptually. It stops short of explicitly naming which sibling to use instead, so it is clear but not fully differentiated.

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 explains the relationship model (belongs to dhost, created by drule), which implicitly tells the agent this is the tool for service-level discovery results rather than host- or rule-level ones. However, it never states when to use this versus dhost_get/drule_get/dcheck_get, and gives no exclusions or prerequisites. Usage is implied, not guided.

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