mcpField
M
mcp-zabbix

mcp-zabbix

Local
github.com/daedalusCloud & Infra0Updated 27w ago

About mcp-zabbix

mcp-zabbix exposes the Zabbix API through an MCP server. It is for MCP clients that need to use Zabbix API operations as tools, with authentication configured through environment variables.

Key features

  1. 01Zabbix API methods exposed as tools
  2. 02Host retrieval and creation operations
  3. 03Token or user-password authentication
  4. 04Python API and CLI entry points

Use cases

  1. 01Retrieving Zabbix host information
  2. 02Creating hosts through an MCP client
  3. 03Using Zabbix API operations in an MCP workflow

MCP support

Exposes Zabbix API methods as tools for MCP clients, including host retrieval and creation operations.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"daedalus-mcp-zabbix": {
"command": "uvx",
"args": [
"mcp-zabbix"
]
}
}
}
Run commanduvx mcp-zabbix

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-zabbix0.1.0

Tools

262

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
paramsanyNo

Details

From the project README

mcp-zabbix

MCP server for Zabbix API - exposes all Zabbix API functionality via MCP

PyPI Python

mcp-name: io.github.daedalus/mcp-zabbix

Install

pip install mcp-zabbix

Configuration

Set the following environment variables:

  • ZABBIX_URL - Zabbix API URL (required)
  • ZABBIX_TOKEN - API token (required, or use user/password)
  • ZABBIX_USER - Zabbix username (optional)
  • ZABBIX_PASSWORD - Zabbix password (optional)

Usage

from mcp_zabbix import mcp

mcp.run()

Or via CLI:

mcp-zabbix

API

The MCP server exposes all Zabbix API methods as tools. Tools follow the pattern:

  • zabbix_<namespace>_<method> (e.g., zabbix_host_get, zabbix_host_create)

Development

git clone https://github.com/daedalus/mcp-zabbix.git
cd mcp-zabbix
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.