Skip to main content
Glama
Sign In
vsphere-console-mcp

vsphere-console-mcp

by Razer0028
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Remote

vm

Destructive

View and control a vSphere virtual machine’s console through vCenter: capture the screen, click, type, and send keys without installing software in the guest.

Instructions

Operate the screen of a VMware vSphere virtual machine through vCenter, the same way its console window does: look takes a picture of the VM's screen, click/move/drag/scroll use its mouse, type/key use its keyboard. Nothing is installed in the VM, so it also works at sign-in and lock screens, BIOS, installers, and when the VM's own network is down. This may be a real machine that people are using: look before acting, and click or type only what the user asked for. Name the VM in every call (vm=...); action='vms' lists them. There is no way to power on/off, reset or reconfigure a VM with this tool. Do not restart, shut down or sign out of a VM from its screen unless the user asked for exactly that.

Actions:

  • vms: the VMs vCenter knows, with power state, guest OS and IP address.

  • look: a picture of the VM's screen (at most max_width pixels wide, default 1568), and the real screen size.

  • click: at rx,ry (0-1000 across and down the screen, as seen in the look picture) or x,y (real screen pixels). button left/right/middle, count=2 for a double-click.

  • move: put the mouse at rx,ry (hover menus, tooltips).

  • drag: press at from_rx,from_ry (or from_x,from_y), move, release at rx,ry (or x,y).

  • scroll: amount notches at rx,ry (positive = up, negative = down).

  • type: type text with the VM's keyboard; only characters on the keyboard ("\n" presses Enter). layout is the guest's keyboard layout (us or jis); symbols come out wrong with the wrong layout.

  • key: press keys, e.g. "ctrl+alt+delete", "win+r", "alt+tab", "tab tab enter" (space-separated). then_look=true returns a new picture after click/move/drag/scroll/type/key. Look again before deciding that an action worked.

Input Schema

NameRequiredDescriptionDefault
xNoScreen x in real pixels (instead of rx)
yNoScreen y in real pixels (instead of ry)
rxNoclick/move/drag/scroll: 0-1000 across the screen
ryNoclick/move/drag/scroll: 0-1000 down the screen
vmNoThe VM: its name in vCenter, its id (vm-123) or its IP address. Required for every action except vms
keysNokey: e.g. "ctrl+alt+delete" or "tab tab enter"
textNotype: the text
countNoclick: 2 = double-click, 3 = triple-click
actionYesWhat to do
amountNoscroll: notches, positive = up, negative = down
buttonNoMouse button
from_xNodrag: start x in real pixels
from_yNodrag: start y in real pixels
layoutNotype/key: the guest's keyboard layout
from_rxNodrag: start, 0-1000 across
from_ryNodrag: start, 0-1000 down
max_widthNolook: largest picture width in pixels (default 1568)
then_lookNoAfter the action, also return a new picture

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (destructiveHint=true, readOnlyHint=false, openWorldHint=true), the description discloses that nothing is installed in the VM so it works at sign-in/lock screens, BIOS, installers and when networking is down, and that this may be a real machine in active use. These are exactly the behavioral traits an agent needs before issuing a mutating action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is front-loaded with the safety-critical constraint ('look before acting') before the action catalog, and every sentence carries actionable information for an 18-parameter, multi-action tool. No filler or restatement of annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still explains what look and vms return (a picture plus real screen size; VMs with power state, guest OS and IP), and covers safety, coordinates, keyboard layout and the absence of power management. Nothing needed to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: rx/ry are explained as 0-1000 relative to the look picture with x/y as real pixels, '\n' presses Enter, wrong layout yields wrong symbols, and key accepts '+'-chained or space-separated sequences. The then_look re-look guidance is also operationally useful.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Operate the screen of a VMware vSphere virtual machine through vCenter') and explicitly distinguishes itself from a console window by explaining the console-equivalent model. The action list further pins down each capability with concrete verbs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Guidance is explicit and operational: 'look before acting', 'click or type only what the user asked for', 'Name the VM in every call', and 'Do not restart, shut down or sign out ... unless the user asked for exactly that'. It also states a hard boundary ('no way to power on/off, reset or reconfigure'), leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools