Model Context Protocol (MCP) server enabling AI agents to control remote desktops
Model Context Protocol (MCP) server enabling AI agents to control remote desktops
A Model Context Protocol (MCP) server that enables AI agents to remotely control Windows, Linux, macOS or anything else that can run a VNC server (don't worry, it's probably fine).
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"vnc-controller": {
"type": "stdio",
"command": "mcp-vnc",
"env": {
"VNC_HOST": "192.168.1.100",
"VNC_PORT": "5900",
"VNC_PASSWORD": "YOUR_VNC_PASSWORD"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| VNC_HOST | Declared in the maintainer’s client configuration. | Check documentation |
| VNC_PORT | Declared in the maintainer’s client configuration. | Check documentation |
| VNC_PASSWORD | Declared in the maintainer’s client configuration. | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Review comments pinned to a running frontend, read and resolved by your coding agent.
Control Android devices with MCP
Lints + auto-fixes how AI coding agents discover any new product. 24 rules, 6 tools, score 0-100.
Windows x64/Python 3.12 MCPB preview: governed local tools and persistent profiles.