Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Zabbix in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Zabbix monitoring: hosts, host groups, items, triggers, active problems, events and the latest measured values. JSON-RPC API over a single endpoint, bearer API token.
Try asking
Example prompts for Zabbix
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Zabbix, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
Zabbix + Gemini
Zabbix monitoring: hosts, host groups, items, triggers, active problems, events and the latest measured values. JSON-RPC API over a single endpoint, bearer API token.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
ZABBIX_URL, ZABBIX_API_TOKEN
Step 1 — Get credentials
Getting a token (requires Zabbix 6.4 or newer)
- Sign in to the Zabbix frontend as a Super admin and open Users → API tokens.
- Create a token for a user with read permission on the host groups the agent should see, and copy the value — Zabbix shows it once.
- Set
ZABBIX_URLto your frontend root (no trailing slash, no/api_jsonrpc.php) andZABBIX_API_TOKENto the token. The adapter sends it asAuthorization: Bearer …, which Zabbix accepts from 6.4 on. Zabbix 5.4–6.2 only take the token in the JSON-RPCauthfield, which this adapter does not use, so every call there fails with "Not authorised".
…(continued in the in-app connector instructions)
Step 2 — Install the adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Step 3 — Add the connector in Gemini
Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (
https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide showsYOUR_SERVER_ID.
Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
"headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
}
}
}
- Get your MCP API key from AnythingMCP → MCP Servers → your server → API keys.
- Save the file and restart
gemini. - Run
/mcpinside the Gemini CLI —Zabbixshould be listed as available. - Vertex AI Studio: pass
https://cloud.anythingmcp.com/mcp/YOUR_SERVER_IDto thetoolsarray of your request with the sameX-API-Keyheader.
Available tools
| Tool | What it does |
|---|---|
zabbix_get_api_version | Read the Zabbix API version |
zabbix_list_hosts | List monitored hosts with their name, status, interfaces and host groups |
zabbix_list_host_groups | List host groups with their id, name and the number of hosts in each |
zabbix_list_problems | List the problems that are active right now, with their severity, host, name and the time they started |
zabbix_list_events | List events from the history — including problems that have since resolved, which problem |
zabbix_list_triggers | List triggers with their expression, severity, current value and the host they belong to — the rules that turn measurements into problems |
zabbix_list_items | List monitored items with their key, name, type, value type and units — what Zabbix actually measures on a host |
zabbix_get_latest_values | Read the most recent value of specific items — the current disk usage, load average or temperature, rather than the alert about it |
zabbix_get_history | Read historical values of one item over a time range — the series behind a graph |
zabbix_list_maintenance_windows | List configured maintenance windows with their hosts, groups and periods — the explanation for why an alert did not fire |
FAQ
Does Gemini 1.5 Pro or 2.x support MCP? Yes — Gemini CLI ≥ 0.4 and Vertex AI tools API both accept MCP httpUrl connectors with custom headers.
Next steps
- Connector landing page
- Connect to Claude
- Connect to ChatGPT
- Connect to Cursor
- Connect to Meta Muse
- Connect to Microsoft Copilot
Was this guide helpful?