---

---

What is this?

MCP (Model Context Protocol) is an open standard that lets AI assistants (ChatGPT, Claude, VS Code Copilot, JetBrains AI, Codex, and others) use external tools. This server exposes the entire Zabbix API as MCP tools — allowing any compatible AI assistant to query hosts, check problems, manage templates, acknowledge events, and perform any other Zabbix operation.

The server runs as a standalone HTTP service. AI clients connect to it over the network.

Features

• Complete API coverage - All 57 Zabbix API groups (220 tools): hosts, problems, triggers, templates, users, dashboards, and more
• Multi-server support - Connect to multiple Zabbix instances (production, staging, ...) with separate tokens
• HTTP + SSE transports - Streamable HTTP (recommended) and SSE for clients like n8n that lack session management
• Tool filtering - Limit exposed tools by category (monitoring, alerts, users, etc.) to stay under LLM tool limits
• LLM-friendly normalizations - Symbolic enum names, auto-fill defaults, preprocessing cleanup, timestamp conversion
• Single config file - One TOML file, no scattered environment variables
• Read-only mode - Per-server write protection to prevent accidental changes
• Rate limiting - Per-client call budget (300/min default) to protect Zabbix from flooding
• Auto-reconnect - Transparent re-authentication on session expiry
• Production-ready - systemd service, logrotate, security hardening
• Generic fallback - zabbix_raw_api_call tool for any API method not explicitly defined

Quick Start

git clone https://github.com/initMAX/zabbix-mcp-server.git
cd zabbix-mcp-server
sudo ./deploy/install.sh
sudo nano /etc/zabbix-mcp/config.toml   # fill in your Zabbix URL + API token
sudo systemctl start zabbix-mcp-server
sudo systemctl enable zabbix-mcp-server

Done. The server is running on http://127.0.0.1:8080/mcp.

Installation

Requirements

• Linux server with Python 3.10+
• Network access to your Zabbix server(s)
• Zabbix API token (User settings > API tokens)

Install

git clone https://github.com/initMAX/zabbix-mcp-server.git
cd zabbix-mcp-server
sudo ./deploy/install.sh

The install script will:

1. Create a dedicated system user zabbix-mcp (no login shell)
2. Create a Python virtual environment in /opt/zabbix-mcp/venv
3. Install the server and all dependencies
4. Copy the example config to /etc/zabbix-mcp/config.toml
5. Install a systemd service unit (zabbix-mcp-server)
6. Set up logrotate for /var/log/zabbix-mcp/*.log (daily, 30 days retention)

Upgrade

cd zabbix-mcp-server
git pull
sudo ./deploy/install.sh update

The update command will upgrade the package to the latest version, refresh the systemd unit and logrotate config, and restart the service if it is running.

Configure

Edit the config file with your Zabbix server details:

sudo nano /etc/zabbix-mcp/config.toml

Minimal configuration - just fill in your Zabbix URL and API token:

[server]
transport = "http"
host = "127.0.0.1"
port = 8080

[zabbix.production]
url = "https://zabbix.example.com"
api_token = "your-api-token"
read_only = true
verify_ssl = true

All available options with detailed descriptions are documented in config.example.toml.

Authentication

The HTTP endpoint can be protected with a bearer token. There are two ways to configure it:

Option 1 - token directly in config:

[server]
auth_token = "your-secret-token-here"

Option 2 - token from environment variable (recommended for production):

[server]
auth_token = "${MCP_AUTH_TOKEN}"

When auth_token is set, all clients must include it in the Authorization header:

Authorization: Bearer your-secret-token-here

When auth_token is not set, the server accepts unauthenticated connections. This is only safe when the server is bound to 127.0.0.1 (default).

Multiple Zabbix servers

You can connect to multiple Zabbix instances. Each tool has a server parameter to select which one to use (defaults to the first defined):

[zabbix.production]
url = "https://zabbix.example.com"
api_token = "prod-token"
read_only = true

[zabbix.staging]
url = "https://zabbix-staging.example.com"
api_token = "staging-token"
read_only = false

Start

sudo systemctl start zabbix-mcp-server
sudo systemctl enable zabbix-mcp-server

Verify the server is running:

sudo systemctl status zabbix-mcp-server

Logs

# Live log stream
tail -f /var/log/zabbix-mcp/server.log

# Via journalctl
sudo journalctl -u zabbix-mcp-server -f

Docker

git clone https://github.com/initMAX/zabbix-mcp-server.git
cd zabbix-mcp-server
cp config.example.toml config.toml
nano config.toml                        # fill in your Zabbix details
docker compose up -d

The config file is mounted read-only into the container. Logs are stored in a Docker volume. Inside the container, host and port from config.toml are overridden (0.0.0.0:8080) for Docker compatibility. To expose on a different host port, change only the left side of the ports: mapping in docker-compose.yml (e.g. "8883:8080").

Upgrade:

git pull
docker compose up -d --build

Logs:

docker compose logs -f

Manual Installation (pip)

If you prefer to install manually without the deploy script:

python3 -m venv /opt/zabbix-mcp/venv
/opt/zabbix-mcp/venv/bin/pip install /path/to/zabbix-mcp-server
/opt/zabbix-mcp/venv/bin/zabbix-mcp-server --config /path/to/config.toml

Connecting AI Clients

The server uses the Streamable HTTP transport by default and listens on http://127.0.0.1:8080/mcp. SSE transport is also available (http://127.0.0.1:8080/sse) for clients that do not support Streamable HTTP session management.

MCP (Model Context Protocol) is an open standard that lets AI assistants use external tools. Any MCP-compatible client can connect to this server - ChatGPT, VS Code, Claude, Codex, JetBrains, and others.

The MCP client configuration is the same for all clients:

{
  "mcpServers": {
    "zabbix": {
      "url": "http://your-server:8080/mcp"
    }
  }
}

Where to put this config depends on the client:

Client	Config location
ChatGPT (initMAX widget)	MCP server settings in the widget configuration
VS Code (Copilot / Continue / Cline)	.vscode/mcp.json or extension settings
Claude Desktop	~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Claude Code	.mcp.json in project root or ~/.claude/settings.json for global
OpenAI Codex	MCP server settings in the Codex configuration
JetBrains IDEs	MCP server settings in the IDE

When auth_token is configured on the server, clients must include the bearer token in requests:

Authorization: Bearer your-secret-token-here

Example Prompts

Once connected, you can ask your AI assistant things like:

Prompt	What it does
"Show me all current problems"	Calls problem_get to list active alerts
"Which hosts are down?"	Calls host_get with status filter
"Acknowledge event 12345 with message 'investigating'"	Calls event_acknowledge
"What triggers fired in the last hour?"	Calls trigger_get with time filter and only_true
"List all hosts in group 'Linux servers'"	Calls hostgroup_get then host_get with group filter
"Show me CPU usage history for host 'web-01'"	Calls host_get, item_get, then history_get
"Put host 'db-01' into maintenance for 2 hours"	Calls maintenance_create
"Export the template 'Template OS Linux'"	Calls configuration_export
"How many items does host 'app-01' have?"	Calls item_get with countOutput
"Check the health of the MCP server"	Calls health_check

The AI chains multiple tools automatically when needed.

Available Tools

All tools accept an optional server parameter to target a specific Zabbix instance (defaults to the first configured server).

Category	Tool	Description
Monitoring	problem_get	Get active problems and alerts — the primary tool for checking what is wrong right now
	event_get / event_acknowledge	Retrieve events and acknowledge, close, or comment on them
	history_get / trend_get	Query raw historical metric data or aggregated trends for capacity planning
	dashboard_* / map_*	Create, update, and manage dashboards and network maps
Data Collection	host_* / hostgroup_*	Manage monitored hosts, host groups, and their membership
	item_* / trigger_* / graph_*	Manage data collection items, trigger expressions, and graphs
	template_* / templategroup_*	Manage monitoring templates and template groups
	maintenance_*	Schedule and manage maintenance periods to suppress alerts
	discoveryrule_* / *prototype_*	Low-level discovery rules and item/trigger/graph prototypes
	configuration_export / _import	Export or import full Zabbix configuration (YAML, XML, JSON)
Alerts	action_* / mediatype_*	Configure automated alert actions and notification channels (email, Slack, webhook, ...)
	alert_get	Query the history of sent notifications and remote commands
	script_execute	Execute global scripts on hosts (SSH, IPMI, custom commands)
Users & Access	user_* / usergroup_* / role_*	Manage user accounts, permission groups, and RBAC roles
	token_*	Create, list, and manage API tokens for service accounts
Administration	proxy_* / proxygroup_*	Manage Zabbix proxies and proxy groups for distributed monitoring
	auditlog_get	Query the audit trail of all configuration changes and logins
	settings_get / _update	View and modify global Zabbix server settings
Generic	zabbix_raw_api_call	Call any Zabbix API method directly by name — use for methods not covered above
	health_check	Verify MCP server status and connectivity to all configured Zabbix servers

Common Parameters (get methods)

Parameter	Description
server	Target Zabbix server name — defaults to the first configured server when omitted
output	Fields to return: extend returns all fields, or pass comma-separated field names (e.g. hostid,name,status)
filter	Exact match filter as JSON object — e.g. {"status": 0} returns only enabled objects
search	Pattern match filter as JSON object — e.g. {"name": "web"} finds all objects containing "web" in the name
limit	Maximum number of results to return — use to avoid large responses
sortfield / sortorder	Sort results by a field name in ASC (ascending) or DESC (descending) order
countOutput	Return the count of matching objects instead of the actual data — useful for statistics

Configuration Reference

All available options with detailed descriptions are in config.example.toml. Quick overview:

Section	Parameter	Description
[server]	transport	"http" (recommended), "sse", or "stdio"
	host	HTTP bind address — 127.0.0.1 (localhost only) or 0.0.0.0 (all interfaces)
	port	HTTP port (default: 8080)
	log_level	debug, info, warning, or error
	log_file	Path to log file (in addition to stderr)
	auth_token	Bearer token for HTTP/SSE authentication (supports ${ENV_VAR})
	rate_limit	Max Zabbix API calls per minute per client (default: 300, set to 0 to disable)
	tools	Filter exposed tools by category or prefix — e.g. ["monitoring", "alerts"] (default: all ~220 tools)
[zabbix.<name>]	url	Zabbix frontend URL
	api_token	API token (supports ${ENV_VAR})
	read_only	Block write operations (default: true)
	verify_ssl	Verify TLS certificates (default: true)

Zabbix Compatibility

Zabbix Version	Status	Notes
7.0 LTS, 7.2, 7.4	Fully supported	All API methods match this version — complete feature coverage
6.0 LTS, 6.2, 6.4	Supported	Core methods work, some newer API methods (e.g. proxy groups, MFA) may return errors
5.0 LTS, 5.2, 5.4	Basic support	Core monitoring and data collection work, newer features unavailable

The server uses the standard Zabbix JSON-RPC API. Methods not available in your Zabbix version will return an error from the Zabbix server — the MCP server itself does not enforce version checks.

Development

git clone https://github.com/initMAX/zabbix-mcp-server.git
cd zabbix-mcp-server
python3 -m venv .venv
source .venv/bin/activate
pip install -e .

Test with MCP Inspector:

npx @modelcontextprotocol/inspector zabbix-mcp-server --config config.toml

Related Projects

Project	Description
Zabbix AI Skills	35 ready-to-use AI workflows for Zabbix — maintenance windows, host onboarding, template upgrades, audits, and more

License

AGPL-3.0 - see LICENSE.

---

---