Provides tools for managing VMware ESXi/vCenter environments, including VM lifecycle operations such as listing, creating, cloning, deleting, powering on/off, and retrieving CPU, memory, storage, and network performance metrics.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ESXi MCP Server list all VMs and show their current CPU and memory usage"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A VMware ESXi/vCenter management server based on MCP (Model Context Protocol), enabling AI assistants like Claude, Gemini, GPT, and others to directly manage virtual machines via stdio JSON-RPC.
stdio transport for direct AI assistant integration (Claude Desktop, Cursor, Gemini, etc.)
ESXi and vCenter Server connections
API key authentication
Complete virtual machine lifecycle management
Real-time performance monitoring
SSL/TLS secure connection support
Flexible configuration (YAML/JSON/Environment Variables)
Related MCP server: VMWare MCP
uvx esxi-mcp-serverMCP config (mcp.json):
{
"mcpServers": {
"esxi-mcp-server": {
"command": "uvx",
"args": ["esxi-mcp-server"],
"env": {
"VCENTER_HOST": "192.168.0.254",
"VCENTER_USER": "administrator@vsphere.local",
"VCENTER_PASSWORD": "your-password",
"VCENTER_INSECURE": "true"
}
}
}
}pip install esxi-mcp-server
esxi-mcp-serverMCP config:
{
"mcpServers": {
"esxi-mcp-server": {
"command": "esxi-mcp-server",
"env": {
"VCENTER_HOST": "192.168.0.254",
"VCENTER_USER": "administrator@vsphere.local",
"VCENTER_PASSWORD": "your-password",
"VCENTER_INSECURE": "true"
}
}
}
}docker pull tai040502/esxi-mcp-serverMCP config:
{
"mcpServers": {
"esxi-mcp-server": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "VCENTER_HOST=192.168.0.254",
"-e", "VCENTER_USER=administrator@vsphere.local",
"-e", "VCENTER_PASSWORD=your-password",
"-e", "VCENTER_INSECURE=true",
"tai040502/esxi-mcp-server"
]
}
}
}Tool | Description |
| Authenticate using API key (required if API key is configured) |
| List all virtual machines |
| Create a new virtual machine |
| Clone a VM from a template or existing VM |
| Delete a virtual machine |
| Power on a virtual machine |
| Power off a virtual machine |
| Get CPU, memory, storage, and network metrics |
All settings can be configured via environment variables:
Env Variable | Description | Required | Default |
| vCenter/ESXi server address | Yes | - |
| Login username | Yes | - |
| Login password | Yes | - |
| Datacenter name | No | Auto-select first |
| Cluster name | No | Auto-select first |
| Storage name | No | Auto-select largest |
| Network name | No | - |
| Skip SSL verification | No |
|
| API access key | No | - |
| Log file path | No | stderr |
| Log level | No |
|
Alternatively, use a YAML or JSON config file:
esxi-mcp-server -c config.yamlPython 3.11+
pyvmomi >= 7.0
pyyaml >= 6.0
mcp[cli]
MIT License
Bright8192
This server cannot be deployed
Manage Vozora VPS servers, SSH keys, firewalls, DNS and usage from an AI agent.
Connect AI assistants to explicitly paired computers, servers, and VMs for permitted remote actions.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Protocol-native energy infrastructure orchestration for AI data centers. Provides 46 MCP tools across 8 grid protocols (IEC-61850, DNP3, Modbus, OCPP, OpenADR, IEEE 2030.5, IEC 60870-5-104, ICCP) with 5 core API primitives: connect, dispatch, settle, comply, and intel. Enables AI agents to programmatically interact with substations, grid interfaces, and energy assets for real-time workload-grid coordination.
