mcp-for-blender

Note: the PyPI package blender-mcp is now mcp-for-blender. Existing setups keep working — uvx blender-mcp still runs the server and no config change is required. New installs should use mcp-for-blender. What changed and why

One command sets up your AI apps and the Blender addon:

macOS / Linux

curl -LsSf https://www.mcp-for-blender.com/install.sh | sh

Windows (PowerShell)

irm https://www.mcp-for-blender.com/install.ps1 | iex

From Command Prompt instead: powershell -c "irm https://www.mcp-for-blender.com/install.ps1 | iex"

Prefer not to run a script, or Windows Defender blocked it? Install uv with winget, open a new terminal, then run setup:

winget install --id=astral-sh.uv -e
uvx mcp-for-blender setup

Already have uv? Run uvx mcp-for-blender setup instead.

It installs uv if needed, finds the MCP clients on your machine (Claude Desktop, Claude Code, Codex, Cursor, VS Code, Devin Desktop/Windsurf, OpenCode, Antigravity), and lets you pick which to set up. Then it installs the Blender addon and enables it. Your existing config is kept: it only adds a blender entry and saves a .bak of each file it changes.

Then fully quit and reopen your AI app (on Windows, quit it from the system tray), open Blender, and ask it to build something. The addon starts its server when Blender opens.

# macOS
brew install uv

# Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
winget install --id=astral-sh.uv -e
# or, with uv's installer
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": ["mcp-for-blender"]
        }
    }
}

claude mcp add blender uvx mcp-for-blender

codex mcp add blender -- uvx mcp-for-blender

uvx mcp-for-blender install-addon

Note: Only run one instance of the MCP server (either Cursor or Claude Desktop), not both.

• Quickstart
• Features
• Premium
• Components
• Installation
  • Automatic setup
  • Prerequisites
  • Make your client find uvx
  • Pin the Python version
  • Install without uv
  • Run with Docker
  • Environment Variables
• MCP Client Setup
  • Claude for Desktop
  • Codex
  • Cursor
  • Visual Studio Code
  • OpenCode
  • Antigravity
• Installing the Blender Addon
• Upgrading (existing users)
• Usage
  • Starting the Connection
  • Using with Claude
  • Capabilities
  • Example Commands
• Persistent API Credentials
• Troubleshooting
• Technical Details
• Limitations & Security Considerations
• Telemetry Control
• Feedback
• Contributing
• Disclaimer
• Star History

Generate AI 3D models (Meshy, Hunyuan3D, Tripo, Hyper3D Rodin) straight into Blender without bringing your own API keys. More details

The system consists of two main components:

1. Blender Addon (addon.py) — a Blender addon that creates a socket server within Blender to receive and execute commands
2. MCP Server (src/blender_mcp/server.py) — a Python server that implements the Model Context Protocol and connects to the Blender addon

The quickest way is the one-line installer. It installs uv, configures your MCP clients, and installs and enables the Blender addon:

# macOS / Linux
curl -LsSf https://www.mcp-for-blender.com/install.sh | sh

# Windows (PowerShell)
irm https://www.mcp-for-blender.com/install.ps1 | iex

Already have uv? Run uvx mcp-for-blender setup instead. On Windows, winget install --id=astral-sh.uv -e installs uv without running a script. See Quickstart for what it changes. The rest of this section covers manual setup.

• Blender 3.0 or newer
• Python 3.10 or newer
• uv package manager

brew install uv

winget install --id=astral-sh.uv -e

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

$localBin = "$env:USERPROFILE\.local\bin"
$userPath = [Environment]::GetEnvironmentVariable("Path", "User")
[Environment]::SetEnvironmentVariable("Path", "$userPath;$localBin", "User")

curl -LsSf https://astral.sh/uv/install.sh | sh

Warning: Do not proceed before installing uv.

MCP clients started from a GUI (Claude Desktop, Cursor, VS Code from the Dock/Start menu) do not inherit your terminal's PATH, so a bare "command": "uvx" can fail with spawn uvx ENOENT even though uvx works in your terminal. If that happens:

• Find uvx's full path — which uvx (macOS/Linux) or where uvx (Windows) — and use it as "command", e.g. /opt/homebrew/bin/uvx or C:\Users\<you>\.local\bin\uvx.exe.
• On Windows you can instead wrap it: "command": "cmd", "args": ["/c", "uvx", "mcp-for-blender"].
• After any PATH or config change, fully quit and relaunch the client (Windows: quit from the system tray, not just the window; macOS: Cmd+Q).

Avoid conda / pyenv / version conflicts.

uv chooses which Python runs the server. On machines with conda (auto-activated base), pyenv, or asdf — or with a newer CPython release that some dependencies do not have wheels for yet — uv can grab an interpreter that makes installation fail. Pin Python 3.11 and prefer uv-managed interpreters to avoid using whatever is on your PATH:

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": ["--python", "3.11", "mcp-for-blender"],
            "env": { "UV_PYTHON_PREFERENCE": "only-managed" }
        }
    }
}

--python 3.11 still satisfies this package's requires-python >=3.10, and UV_PYTHON_PREFERENCE=only-managed keeps uv from selecting conda, pyenv, asdf, or system Python first. (The repo's .python-version is only a hint for contributors and does not affect uvx.)

If a previous failed attempt keeps replaying after a fix, clear the cache:

uv cache clean mcp-for-blender blender-mcp && uvx --refresh mcp-for-blender

On locked-down machines you can skip uvx entirely with pipx, then point your client at the installed command:

pipx install mcp-for-blender
pipx ensurepath          # then restart your shell / client

Use the resulting absolute path as "command" (find it with which mcp-for-blender / where mcp-for-blender) and omit args.

You can run the MCP server in a container instead of installing it. Blender itself still runs on your machine — the container only hosts the MCP server, which connects out to the Blender addon.

Build the image from the repo root:

docker build -t mcp-for-blender .

Then point your MCP client at it (the -i flag is required — the server talks to the client over stdin/stdout):

{
    "mcpServers": {
        "blender": {
            "command": "docker",
            "args": ["run", "-i", "--rm", "mcp-for-blender"]
        }
    }
}

The image defaults to BLENDER_HOST=host.docker.internal, which reaches the host's Blender out of the box with Docker Desktop on macOS and Windows.

On Linux, host.docker.internal doesn't exist and the addon only listens on localhost, so use host networking instead:

{
    "mcpServers": {
        "blender": {
            "command": "docker",
            "args": ["run", "-i", "--rm", "--network=host", "-e", "BLENDER_HOST=localhost", "mcp-for-blender"]
        }
    }
}

To enable safe mode in the container, add "-e", "BLENDER_MCP_SAFE_MODE=1" to args.

The following environment variables can be used to configure the Blender connection:

Example:

export BLENDER_HOST='host.docker.internal'
export BLENDER_PORT=9876

You can also pass the connection as CLI flags, which take precedence over the environment variables. This is handy for running several Blender instances side by side, since each MCP client entry can point at a different port with plain arguments instead of env vars:

uvx mcp-for-blender --port 9877

In an MCP client config that means a second entry differing only in args:

{
  "mcpServers": {
    "blender": { "command": "uvx", "args": ["mcp-for-blender"] },
    "blender-b": { "command": "uvx", "args": ["mcp-for-blender", "--port", "9877"] }
  }
}

Each instance needs its own port set in the Blender addon panel to match.

Note: the addon's socket server has no authentication or encryption, so anyone who can reach that port can run Python inside Blender. Keep it on localhost unless you are on a trusted network, and prefer an SSH tunnel over pointing --host/BLENDER_HOST at a remote machine directly.

By default, the AI can run any Python code in Blender. Set BLENDER_MCP_SAFE_MODE=1 to check every script before it runs and block risky code — things like reading or writing files directly, running other programs, accessing the network, or installing code that keeps running after the script ends. Normal Blender work (modeling, materials, rendering, saving, import/export) still works. Blocked scripts are sent back to the AI with the reason, so it can try again with a corrected version.

Watch the setup instruction video (assuming you have already installed uv)

Go to Claude → Settings → Developer → Edit Config → claude_desktop_config.json and include the following:

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": [
                "mcp-for-blender"
            ]
        }
    }
}

claude mcp add blender uvx mcp-for-blender

The Codex CLI, desktop app, and IDE extension all share the same config file (~/.codex/config.toml), so setting the server up once covers all three.

The plugin adds a live viewport inline in the chat (click an object to attach it to your next message), thumbnail pickers for Poly Haven, Sketchfab and Poly Pizza, and @-mentions for scene objects, materials and collections. It isn't in the Codex plugin directory yet, so add it from this repo:

git clone https://github.com/ahujasid/blender-mcp.git
codex plugin marketplace add ./blender-mcp/integrations/codex

Then restart Codex, install MCP for Blender from the plugins directory, and ask it to use MCP for Blender in chat. Once it's running, the viewport opens in a side panel next to the conversation:

Register the server with the Codex CLI:

codex mcp add blender -- uvx mcp-for-blender

Or add it by hand to ~/.codex/config.toml (or $CODEX_HOME/config.toml):

[mcp_servers.blender]
command = "uvx"
args = ["mcp-for-blender"]

Or in the Codex desktop app: Settings → MCP servers → Add server → name it blender, pick STDIO, enter uvx mcp-for-blender as the command, then Save and restart. If the app can't find uvx, use its full path instead — see Make your client find uvx.

Check it registered with codex mcp list — the blender server should show as enabled. The tools become available the next time you start Codex.

To set environment variables (e.g. a non-default Blender host/port), pass --env KEY=VALUE flags to codex mcp add, or add them in the config file:

[mcp_servers.blender]
command = "uvx"
args = ["mcp-for-blender"]
env = { BLENDER_HOST = "localhost", BLENDER_PORT = "9876" }

macOS — go to Settings → MCP and paste the following:

• To use as a global server, use the "add new global MCP server" button and paste
• To use as a project-specific server, create .cursor/mcp.json in the root of the project and paste

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": [
                "mcp-for-blender"
            ]
        }
    }
}

Windows — go to Settings → MCP → Add Server, add a new server with the following settings:

{
    "mcpServers": {
        "blender": {
            "command": "cmd",
            "args": [
                "/c",
                "uvx",
                "mcp-for-blender"
            ]
        }
    }
}

Cursor setup video

Note: Only run one instance of the MCP server (either on Cursor or Claude Desktop), not both.

Prerequisites: Make sure you have Visual Studio Code installed before proceeding.

{
  "mcp": {
    "blender-mcp": {
      "type": "local",
      "command": ["uvx", "mcp-for-blender"],
      "enabled": true,
      "environment": {
        "BLENDER_HOST": "localhost",
        "BLENDER_PORT": "9876"
      }
    }
  }
}

{
  "mcpServers": {
    "blender-mcp": {
      "command": "uvx",
      "args": ["mcp-for-blender"],
      "env": {
        "BLENDER_HOST": "localhost",
        "BLENDER_PORT": "9876"
      }
    }
  }
}

uvx mcp-for-blender setup (see Quickstart) does all of this, including enabling the addon. The steps below are for doing it by hand.

1. Recommended — from a terminal, run:

uvx mcp-for-blender install-addon

This copies the addon into your Blender addons folder as blender_mcp.py. It prints where it wrote to, and keeps a .bak of any file it replaces.

Optional: uvx mcp-for-blender addon-paths lists detected Blender addons folders. Override the destination with BLENDERMCP_ADDONS_DIR=/path/to/scripts/addons.

2. Open Blender

3. Go to Edit → Preferences → Add-ons

4. Enable Interface: MCP for Blender (search "MCP for Blender"). If it doesn't appear yet, click Install… and select the copied blender_mcp.py / addon.py, or restart Blender.

5. Manual alternative — if the command above can't find your Blender install, or you prefer doing it by hand: download addon.py from this repo → in Blender, Edit → Preferences → Add-ons → Install… → select the downloaded addon.py → enable it.

Then open the MCP for Blender tab in Blender's sidebar (press N in the 3D viewport) and click Start MCP Server. See Starting the Connection below.

For newcomers, go straight to Quickstart. For existing users, see below.

1. Run:

uvx mcp-for-blender@latest update

This updates the MCP server (refreshing uv's cached copy, or upgrading a uv tool install) and every installed copy of the Blender addon, keeping a .bak of each file it replaces. It never downgrades an addon that's newer than the release, and leaves alone a copy you've edited locally. Add --dry-run to see what it would change first.

Use @latest the first time: releases older than 2.1.7 don't have the update command, and uvx may still have one of those cached.

2. Restart your MCP client (Claude Desktop, Cursor, ...) so it starts the new server.

3. In Blender: restart it, or Preferences → Add-ons → disable and re-enable Interface: MCP for Blender, then click Start MCP Server again.

If a client is still set up with the old blender-mcp package name, update says so; uvx mcp-for-blender setup switches it over.

Note: the MCP server never modifies your Blender addon files on its own. When it starts, it checks whether the installed addon is behind the bundled copy and logs how to update; update and install-addon are what actually write. Trajectory capture still works on older loaded addons via an execute_code fallback.

1. In Blender, go to the 3D View sidebar (press N if not visible)
2. Find the MCP for Blender tab
3. Turn on the checkboxes you'd like to use (see more under Capabilities below)
4. Click Connect to Claude
5. Make sure the MCP server is running in your terminal

Once the config file has been set on Claude, and the addon is running on Blender, you will see a hammer icon with tools for MCP for Blender.

The AI writes Blender Python itself for modelling, layout, materials, animation, rigging and retopology. The MCP adds what Python can't do on its own, as nine tools:

Which Tencent Cloud service the addon must call depends on where your account lives:

International credentials sent to the mainland endpoint fail with AuthFailure.SignatureFailure or ResourceUnavailable, so tick the toggle when your SecretId/SecretKey come from tencentcloud.com. The toggle sits under Tencent Hunyuan 3D → Official API in the sidebar.

Tripo generates textured 3D models from a text prompt or a reference image. It runs through Premium with no key, or on your own Tripo API key. Through Premium, text uses your default quality and an image counts as one high-quality generation. Get a Tripo API key. Tick Tripo under AI Model Generation in the sidebar, choose a Model, and paste the key.

Meshy generates textured 3D models from a text prompt or a reference image, sized to real-world height with the origin at the bottom, so models arrive standing on the ground at a plausible size. It runs through Premium with no key, or on your own Meshy API key. Through Premium, Meshy uses its latest model and each model counts as one standard generation. Your own API key needs a paid Meshy plan: get a Meshy API key. Tick Meshy under AI Model Generation in the sidebar, choose a Model, and paste the key. On your own key, ask for a character "in an A-pose" or "in a T-pose" and Meshy generates it in that pose, ready to rig.

Poly Haven publishes around 2,400 HDRIs, textures and models, all CC0 and free, funded by donations rather than by selling the assets. There is no API key, no account and no rate limit worth worrying about.

In the 3D View sidebar, tick Poly Haven. That is the whole setup.

Worked example:

"Light the scene with an overcast afternoon HDRI and put a rusty metal texture on the wall"

Claude calls search_assets(source="polyhaven", query="overcast afternoon", asset_type="hdris"), which understands the intent rather than matching keywords - "couch" finds sofas, and it works in any language. previews=3 attaches thumbnails of the top results before spending the bandwidth, and import_asset(source="polyhaven", id="...", asset_type="textures", apply_to=["Wall"]) downloads a texture and applies it in one call.

Searches can also filter on a category path or on attributes such as weather and time of day for HDRIs, or surface use and condition for textures; an unknown attribute errors with the valid ones.

Models are imported from the .blend, which is the file the artist authored - the glTF, FBX and USD versions are generated from it and lose material detail. Textures build a Principled material from the maps that drive it, and skip the repackings and alternate conventions that nothing reads. HDRIs are packed into the file, so the lighting survives being saved and reopened somewhere else, and arrive in a new world rather than overwriting one you built.

Licence and attribution: every Poly Haven asset is CC0. You never have to credit anyone, for anything, commercial or not. Their API terms do ask that software built on the live API makes clear where the assets come from, so the search and import responses name the source and link the asset's page. On import, polyhaven_id, polyhaven_url, polyhaven_authors, polyhaven_resolution and polyhaven_licence are written onto the imported objects, materials, images and world as custom properties, so whoever opens the .blend later can still find the asset and the artist who made it.

Poly Pizza hosts roughly 10,600 free low-poly models, including the rescued Google Poly archive. It is the best source for stylised game assets: every model is a single self-contained .glb, and the geometry is far lighter than Sketchfab's.

1. Get a free API key at poly.pizza/settings/api
2. In the 3D View sidebar, tick Use assets from Poly Pizza
3. Paste the key into the API Key field that appears (or store it permanently under Edit → Preferences → Add-ons → MCP for Blender)

Worked example:

"Search Poly Pizza for a low-poly chair under a CC0 licence and import one at 1 metre tall"

Claude calls search_assets(source="polypizza", query="chair", licence="CC0"), which returns each match with its licence and triangle count, then import_asset(source="polypizza", id="...", target_size=1.0).

You can also filter by category ("Animals", "Furniture & Decor", "Transport", "Nature", "Buildings", "People & Characters", "Food & Drink", "Weapons", "Clutter", "Objects", "Scenes & Levels", "Other") or ask for animated models only.

Attribution: about 69% of the Poly Pizza catalogue is CC-BY, which requires you to credit the creator wherever the model appears. On import, the ready-formatted credit line is written onto each imported root object as the custom property polypizza_attribution (alongside polypizza_id and polypizza_licence), so it is saved into your .blend and survives the session. Filter with licence="CC0" if you would rather use models that need no credit.

Here are some examples of what you can ask Claude to do:

MCP for Blender supports persistent credentials via Blender Add-on Preferences:

Edit → Preferences → Add-ons → MCP for Blender

You can store these values there so they survive Blender restarts:

• Sketchfab API Key
• Poly Pizza API Key
• Hyper3D API Key
• Hunyuan3D SecretId / SecretKey
• Hunyuan3D API URL
• Meshy API Key
• Tripo API Key

For headless setups or CI, credentials can also be injected by environment variables:

The system uses a simple JSON-based protocol over TCP sockets:

• Commands are sent as JSON objects with a type and optional params
• Responses are JSON objects with a status and result or message

Warning: The execute_blender_code tool allows running arbitrary Python code in Blender, which can be powerful but potentially dangerous. Use with caution in production environments. ALWAYS save your work before using it.

• Poly Haven requires downloading models, textures, and HDRI images. If you do not want to use it, please turn it off in the checkbox in Blender.
• Complex operations might need to be broken down into smaller steps.

Telemetry is opt-in. Collection of your content is off by default and stays off until you explicitly turn it on.

What is collected by default (no opt-in): a minimal anonymous usage record so I can count active users and see which tools get used — a randomly generated install ID, a session ID, the tool name, whether it succeeded, how long it took, the MCP for Blender and Blender versions, your operating system, and a timestamp.

Never collected without opting in: your prompts, generated code, viewport screenshots, scene data, and trajectory steps.

To opt in — go to Edit → Preferences → Add-ons → MCP for Blender and check the telemetry consent checkbox. Some MCP clients will also offer you a one-time opt-in prompt at the start of a conversation. Opting in adds prompts, generated code, screenshots, and trajectory data to what's collected; see the TnC for details. You can turn it back off in the same place at any time.

To turn off telemetry entirely, including the minimal anonymous usage record, set an environment variable:

DISABLE_TELEMETRY=true uvx mcp-for-blender

Or add it to your MCP config:

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": ["mcp-for-blender"],
            "env": {
                "DISABLE_TELEMETRY": "true"
            }
        }
    }
}

Telemetry data is not linked to your name or account. It may be used to improve MCP for Blender, for research, and to train AI models.

Full detail on what is collected, and the license you grant by opting in, is in TERMS_AND_CONDITIONS.md.

We are actively looking for feedback on MCP for Blender. If you have thoughts, share them here.

If you have more detailed feedback, you can schedule a call with us here — we will credit you in the project.

Give feedback, get inspired, and build on top of the MCP: Discord

Contributions are welcome! Please feel free to submit a Pull Request.

This is a third-party integration and not made by Blender. Made by Siddharth.