VMware MCP Server
Enables management of VMware Workstation virtual machines, including lifecycle and snapshot operations, through MCP tools accessible by AI assistants.
README
VMware MCP Server
MCP server for managing VMware Workstation virtual machines via the
vmrest.exe REST API. Exposes VM lifecycle and snapshot operations as
MCP tools that can be consumed by any MCP-compatible AI assistant.
Prerequisites
- Python >= 3.11
- VMware Workstation Pro 17+ with the REST API service enabled
(
vmrest.exerunning on port 8697 by default) - uv (recommended) or
pip
Quick Start
# Clone / open the project directory
cd VMwareMCP
# Create a virtual environment and install
uv venv
uv pip install -e .
# Set at least one host (use your Windows credentials)
export VMREST_HOST_1=localhost
export VMREST_USERNAME_1=your_username
export VMREST_PASSWORD_1=your_password
# Run the server
uv run vmware-mcp
Environment Variables
Each host uses a numbered suffix (_1, _2, …). The server scans
sequentially and stops at the first missing VMREST_HOST_N.
| Variable | Required | Default | Description |
|---|---|---|---|
VMREST_HOST_N |
Yes | — | Hostname or IP address |
VMREST_PORT_N |
No | 8697 |
vmrest API port |
VMREST_USERNAME_N |
Yes | — | Windows username (Basic Auth) |
VMREST_PASSWORD_N |
Yes | — | Windows password (Basic Auth) |
VMREST_VERIFY_SSL_N |
No | false |
Verify self-signed certificate |
VMREST_ALIAS_N |
No | host-N |
Friendly name for this host |
Example (two hosts)
# Host 1 – local workstation
export VMREST_HOST_1=localhost
export VMREST_USERNAME_1=Admin
export VMREST_PASSWORD_1=secret
export VMREST_ALIAS_1=my-pc
# Host 2 – remote dev server
export VMREST_HOST_2=192.168.1.100
export VMREST_USERNAME_2=Admin
export VMREST_PASSWORD_2=secret2
export VMREST_ALIAS_2=dev-server
Transport
The server defaults to streamable-http on port 51001.
- Server URL:
http://localhost:51001/mcp - Override with
--transport stdiofor stdio mode
MCP Client Configuration
streamable-http (default)
{
"mcpServers": {
"vmware": {
"url": "http://localhost:51001/mcp"
}
}
}
stdio
{
"mcpServers": {
"vmware": {
"command": "uv",
"args": ["run", "vmware-mcp", "--transport", "stdio"]
}
}
}
Project Structure
VMwareMCP/
├── src/vmware_mcp/
│ ├── server.py # FastMCP server entry point
│ ├── client_manager.py # Multi-host client pool
│ ├── vmrest_client.py # HTTP client for single vmrest host
│ ├── models.py # Pydantic data models
│ └── config.py # Environment-based configuration
├── pyproject.toml
└── README.md
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.