Log inSubmit server
KeyShot MCP logo

KeyShot MCP

Controls saved KeyShot scenes, materials, cameras, environments, previews, and headless renders through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install KeyShot MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "keyshot-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "keyshot-mcp"
      ],
      "env": {
        "KEYSHOT_HEADLESS_EXE": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 19 tools correctly (3d ago).

Overview

KeyShot MCP MCP server connects an MCP-compatible agent to local KeyShot headless scripting for saved-scene inspection, editing, previews, and renders. It can import models, apply materials, configure cameras and environments, save scene copies, and render selected or multiple views. Use it when an agent needs to work from saved .bip scenes without controlling the open KeyShot GUI. The tested setup uses Node.js 20+, a locally installed licensed KeyShot edition with headless scripting, and Windows 11 with KeyShot Studio 2025 or KeyShot 14.1.

Use cases

  • Inspect a saved KeyShot scene before editing
  • Apply a material to one selected object
  • Create previews for agent-assisted visual review
  • Render several saved camera views
  • Import a model and save a scene copy

Key features

  • Saved-scene inspection and synchronization
  • Material, camera, and environment controls
  • PNG preview rendering
  • Single, batch, all-camera, and queued renders
  • Headless KeyShot startup diagnostics
  • Scene copy and controlled output workflows

Tools19

What KeyShot MCP lets your agent do. Expand a tool for its parameters.

Verified live~7.3k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

8/8 checks healthy over the last 50d

What it can do

From the 19 tools this server returned when we ran it; 19 declare their own safety hints.

Can delete or modify data · 13Read-only tools · 6
Network at startup3 connections
Files written at startupNone
Install scriptsprepare
npm provenanceSigned build
Package age108 days
Maintainers1

Observed 2026-10-25 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · keyshot-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars25Stargazers on the source repository.
npm downloads750Package downloads in the last 30 days.
Last commit7d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed19Callable tools this server registers over MCP.

How KeyShot MCP works

What KeyShot MCP MCP server does

KeyShot MCP MCP server lets an MCP-compatible agent work with saved KeyShot scenes through local headless scripting. It can inspect scene metadata, objects, cameras, materials, model sets, and references; import models; apply named materials or local material files; and save an existing scene to a controlled output path.

Rendering workflows can use a selected or active camera, every saved camera, a chosen group of cameras, or a sequential queue of independent jobs. The server also supports preview renders that return PNG content to the agent for visual review. A product-render workflow can prepare a scene, save a copy, and render it in one KeyShot process.

The server works with saved files rather than the live KeyShot window. It does not read edits that have not been saved in the scene file, and it does not provide real-time GUI control.

How it works

The KeyShot MCP MCP server runs on the same computer as KeyShot and starts KeyShot in headless mode. An agent calls the available MCP tools, which perform operations against saved scenes and configured output locations. The status tool checks local configuration, output access, presets, and whether KeyShot can start with the configured setup.

A typical workflow begins with status and scene inspection. The agent can then adjust a selected object’s material, create or update a camera, choose an environment, and request a preview. Temporary preview images are returned to the agent and removed after reading; a path can be supplied when a persistent image is required. After review, the agent can render the selected view or produce several views.

The sync workflow detects changes to a saved scene, copies the newest version safely, and returns a preview. Operations are intended to work on scene copies so the original saved scene is not overwritten by the normal product-render flow.

Setup and configuration

The KeyShot MCP MCP server requires Node.js 20 or newer, an MCP-compatible client, and a locally installed, licensed KeyShot edition that supports headless scripting. The documented tested environment is Windows 11 with KeyShot Studio 2025 or KeyShot 14.1.

Install the npm package with npx -y keyshot-mcp@0.13.5, or install it globally and use the keyshot-mcp command. A source build is also supported with pnpm, followed by running the generated dist/index.js with Node. Configure KEYSHOT_HEADLESS_EXE with the full path to the local keyshot_headless.exe.

After adding the server to the client’s MCP configuration, restart or reload the client and call keyshot_status. A successful setup reports ready: true after checking the executable, output access, bridge, presets, and a minimal KeyShot startup. KeyShot software, licenses, and library assets are not bundled with the server.

Tools and capabilities

The documented tools cover these areas:

  • Diagnose executable, output, preset, bridge, and startup configuration.
  • Inspect scenes and list saved cameras, camera presets, and material presets.
  • Import models into an empty or base scene and save the result.
  • Apply materials by KeyShot material name, local file, or configured preset.
  • Create or update camera transforms, distance, field of view, or focal length.
  • Select or adjust an environment, including brightness and rotation.
  • Produce previews, single-camera renders, batch camera renders, all-camera renders, and queued jobs.
  • Copy changed saved scenes, save scenes, and run combined product-render workflows.

Limitations and notes

Results returned by tools, including scene information and previews, are delivered to the MCP client’s agent. Depending on that client’s implementation and model configuration, the content may be sent to the selected model provider. The server itself does not upload this material, but confidential projects should be reviewed against the project’s privacy and security requirements.

The server depends on a valid local KeyShot installation and headless scripting support. Because it operates on saved scenes, users must save changes before asking the agent to inspect or synchronize them.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about KeyShot MCP

KeyShot MCP is an MCP server that connects an MCP-compatible agent to local KeyShot headless scripting. Its main tools inspect and synchronize saved scenes, import models, apply materials, configure cameras and environments, return PNG previews, and run single, batch, all-camera, or queued renders without controlling the open KeyShot window.

Install it with `npx -y keyshot-mcp@0.13.5` and configure the client to run that command. Set `KEYSHOT_HEADLESS_EXE` to the full local path of `keyshot_headless.exe`, reload the client, and run `keyshot_status` to verify the setup.

It requires Node.js 20 or newer, an MCP-compatible client, and a locally installed licensed KeyShot edition with headless scripting. Windows 11 with KeyShot Studio 2025 or KeyShot 14.1 is the tested configuration; software licenses and library assets are not included.

No. It operates on saved scenes through local headless scripting and cannot read unsaved edits or control the active KeyShot GUI session. Save the scene before asking the agent to inspect, synchronize, modify, preview, or render it.

Related MCP servers

All in Architecture & Design All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewKeyShot MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/keyshot-mcp?style=directory)](https://allmcps.com/mcp/keyshot-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/keyshot-mcp"><img src="https://allmcps.com/api/badge/keyshot-mcp?style=directory" alt="KeyShot MCP on AllMCPs" /></a>