
Zabbix API MCP
Connects Claude to your Zabbix monitoring infrastructure through the Zabbix API. You get tools to pull daily monitoring briefs, query current problems, inspect host configurations, and retrieve item metrics. Reach for this when you want to troubleshoot infrastructure issues conversationally instead of clicking through the Zabbix web interface, or when you need to correlate monitoring data with logs and documentation during incident response. Saves you from context switching between Claude and your monitoring dashboard when investigating alerts or reviewing system health.
- tools
- 8
- transport
- STDIO
- last updated
- Oct 18, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
health_checkServer version, Zabbix connectivity/auth, detected API version, and configured daily_brief categories — call at session start or after a timeout
Server version, Zabbix connectivity/auth, detected API version, and configured daily_brief categories — call at session start or after a timeout
No parameter schema in public metadata yet.
daily_briefMorning patrol: active problems (Warning+), hosts currently in maintenance, plus one section per configured category
Morning patrol: active problems (Warning+), hosts currently in maintenance, plus one section per configured category
No parameter schema in public metadata yet.
get_problemsActive problems by severity and tag, newest-first with age; header shows the true total (showing N of TOTAL when capped); problems on disabled triggers, hosts or items are hidden as in the Zabbix frontend (include_disabled=True lists them); output includes eventid
Active problems by severity and tag, newest-first with age; header shows the true total (showing N of TOTAL when capped); problems on disabled triggers, hosts or items are hidden as in the Zabbix frontend (include_disabled=True lists them); output includes eventid
No parameter schema in public metadata yet.
get_hostsList hosts filtered by role/tag/group, with IP and tags
List hosts filtered by role/tag/group, with IP and tags
No parameter schema in public metadata yet.
get_host_itemsCurrent item values for a host (server-side host filter)
Current item values for a host (server-side host filter)
No parameter schema in public metadata yet.
acknowledge_problemAcknowledge problems and add a message (does not close them)
Acknowledge problems and add a message (does not close them)
No parameter schema in public metadata yet.
set_maintenanceOpen an idempotent Zabbix maintenance window, selecting hosts by location tag or by exact host name (exactly one of the two)
Open an idempotent Zabbix maintenance window, selecting hosts by location tag or by exact host name (exactly one of the two)
No parameter schema in public metadata yet.
get_maintenance_windowsList maintenance windows (Active/Upcoming/Expired) — cross-check before treating another tool's alert as a new incident
List maintenance windows (Active/Upcoming/Expired) — cross-check before treating another tool's alert as a new incident
No parameter schema in public metadata yet.
Sponsors
Readme
zapi-mcp
English | 日本語
MCP (Model Context Protocol) server for the Zabbix API.
Built for network operations: a single daily_brief call summarizes active
problems plus site-specific categories (DHCP pool usage, SNAT session usage,
core-network problems, …), and individual tools query problems, hosts, and item
values. Organization-specific tags live in a config file, not the code, so the
server stays generic.
Version-adaptive auth: works against Zabbix 6.0 LTS (user + auth field) and
forward-compatible with 6.4 / 7.0 (username + Authorization: Bearer).
Documentation: https://shigechika.github.io/zapi-mcp/
Features
Details
- Repository
- github.com/shigechika/zapi-mcp
- Package
zapi-mcp- Transport
- STDIO
- Registry
- MCP registry, active