Kvm MCP Server

Smart hands for your AI agents - write-capable KVM+BMC+SSH MCP server: gated, verified, audited.

Local serverstdioPython

What is the Kvm MCP server?

Kvm MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Smart hands for your AI agents - write-capable KVM+BMC+SSH MCP server: gated, verified, audited.

What you get

kvm-pilot lets an agent drive a headless box through POST, firmware, the bootloader, and an OS install with no agent on the target: it works at the pixel level through an IP-KVM (PiKVM, the GL.iNet GLKVM fork GL-RM1 / GL-RM1PE, BliKVM), at the structured-state level through a BMC (Redfish on iDRAC/iLO/OpenBMC, IPMI on BMCs that predate Redfish), at the firmware level through Intel AMT/vPro (a BIOS/POST/GRUB screenshot + power + SOL on a business laptop an HDMI-capture KVM can't see boot on), and over SSH once an OS is up. A pluggable vision subsystem reads a KVM screenshot and tells you what boot phase

Setting it up

The server ships on PyPI as kvm-pilot, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Kvm is connected, these are the calls the assistant has available:

  • dry — run** short-circuits first: it logs the intended call and skips it
  • confirmation — a callback that can veto any destructive call that would
  • Vision — based boot-phase detection** — classify BIOS/GRUB/installer/crash
  • GLKVM — fork awareness** — documents the API-enable prerequisite and GL
  • Stdlib — only client core** — the driver/vision code imports only the standard
  • Plane — Read
  • Device — Status
  • BliKVM — Expected to work (PiKVM-compatible API); untested

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the kvm mcp server does with a few real requests.

Choosing this one

Plenty of monitoring and observability servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Kvm's toolset — dry, confirmation, Vision and 5 more — is a fair guide to whether it matches your workflow. It is maintained by DustinTrap; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
dryrun** short-circuits *first*: it logs the intended call and skips it
confirmationa callback that can veto any destructive call that would
Visionbased boot-phase detection** — classify BIOS/GRUB/installer/crash
GLKVMfork awareness** — documents the API-enable prerequisite and GL
Stdlibonly client core** — the driver/vision code imports only the standard
PlaneRead
DeviceStatus
BliKVMExpected to work (PiKVM-compatible API); untested

How to install the Kvm MCP server

{
  "mcpServers": {
    "kvm-pilot": {
      "command": "uvx",
      "args": ["kvm-pilot"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Kvm to dry.
  • Use Kvm to confirmation.
  • Use Kvm to Vision.

Frequently asked questions

It connects Kvm to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (dry, confirmation, Vision, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Kvm directly.