# Blender MCP and the Future of Creative Tools - Siddharth Ahuja

Siddharth Ahuja

AI Engineer World's Fair 2025

[Talk page](https://ai.engineer/talks/nnktgWtfJHE-blender-mcp-future-creative-tools) · [Video](https://www.youtube.com/watch?v=nnktgWtfJHE)

## Blender MCP and the Future of Creative Tools

Blender’s scripting interface lets a language model turn a scene description into operations. Siddharth Ahuja’s experiments show why distinct tools matter, and how the same approach can connect generated objects, animation, and music.

### Why a donut becomes an interface problem

[0:20](https://www.youtube.com/watch?v=nnktgWtfJHE&t=20s)

Making a donut sounds like a modest creative goal. In **Blender**, getting there can first mean learning a substantial interface. Siddharth Ahuja came to the problem through experimentation after running a product studio: he liked what the application could do, but had never mastered its controls.

Blender is a general-purpose 3D application. It can import assets, animate them, create artwork, and export work to a game engine. Those capabilities come with tabs across the top, properties on the right, and more options nested inside them. Ahuja jokes that navigating all those controls had kept him from becoming a good 3D artist.

When he encountered **Model Context Protocol**, or MCP, its promise of connecting a language model to tools suggested a different entry point. Could the model handle the operations while he described what he wanted?

Ahuja describes a beginner donut course he followed as a five-hour exercise. His frustration was the distance between a simple intention and the knowledge needed to carry it out. The question behind Blender MCP was whether prompting could shorten that distance.

![The starting point is Blender’s full interface, even when the goal is only a simple object.](https://ai.engineer/api/talk-essay-media/40fecead17deb3c223d8de0eb92e1c5872456719e9fbef541794d04d6048cbc7)

The starting point is Blender’s full interface, even when the goal is only a simple object.

### A dragon that gets the brief

[1:57](https://www.youtube.com/watch?v=nnktgWtfJHE&t=117s)

[Blender MCP](https://github.com/ahujasid/blender-mcp) connects a model application, such as **Claude** or **ChatGPT**, to Blender so that a prompt can produce scene operations. Ahuja’s opening demonstration asks for a dragon guarding a pot of gold. The user supplies the scene’s intent; the model application works out how to construct it.

Ahuja laughs at the result: it understands the assignment, even if it is hardly exceptional artwork. There is an isometric room, a dragon with wings, and a pot of gold. Ahuja estimates that the dragon scene took about five minutes to make. He thinks the same attempt would have taken him much longer manually.

**Getting a recognizable result and producing polished artwork are separate achievements.** This dragon demonstrates the first: a description has become an arrangement of objects inside a complex creative application.

At the time of the talk, Ahuja reported approximately 11,500 GitHub stars for Blender MCP. He also reported more than 160,000 downloads. Other people were already using it and building on it, expanding the experiments beyond what he could make himself.

### The model selects tools; Blender executes the work

[3:25](https://www.youtube.com/watch?v=nnktgWtfJHE&t=205s)

The connection is simpler than the resulting scenes might suggest. A model application communicates with Blender through MCP, which provides a standardized way to expose available capabilities. Ahuja’s sketch puts the application between Blender and external asset services: it can coordinate work inside the local scene and requests to outside APIs.

![Ahuja’s sketch connects Blender script execution, a client and external asset APIs.](https://ai.engineer/api/talk-essay-media/23aba480b7d60976faf0cc38f47ecc76f0d30714c93e134743bf360e95853d6b)

Ahuja’s sketch connects Blender script execution, a client and external asset APIs.

**Tool descriptions** tell the model which operations are available. The model selects an operation, and the application invokes it; MCP itself does not choose what to make.

On the Blender side, Ahuja’s add-on executes scripts supplied through the bridge. That is the crucial connection between language and geometry: generated code becomes operations inside Blender. The model application interprets the request, while Blender executes the scene work.

Assets extend the available vocabulary beyond objects constructed directly through scripts. **Rodin** supplies AI-generated assets, while Sketchfab and Poly Haven provide other asset sources. The model application can coordinate obtaining an object and bringing it into the scene.

Blender makes this practical because it already supports **scripting** and can download and import assets. The integration can use those existing capabilities instead of reproducing each action as a sequence of clicks through the interface.

For example, a user can describe a zombie and ask for a generated asset that fits the description. The client coordinates that request with the external service and the work inside Blender. This is its role as an **orchestrator**: the creative request may require several capabilities, but they can contribute to one result.

Ahuja presents the separation between application, model, and creative tool as a source of flexibility. He names Claude, Cursor, Windsurf, and LangChain as possible environments, and points to choices across Claude, ChatGPT, and **Gemini** for the model side. His design ambition is to let people bring their preferred environment and model to the same creative workflow.

### Distinct tools reduce selection ambiguity

[5:47](https://www.youtube.com/watch?v=nnktgWtfJHE&t=347s)

The first implementation lesson is how much work an existing scripting interface removes. Claude’s ability to write code becomes useful for modeling and asset handling because Blender can execute that code. A general execution capability can reach many parts of the application without requiring a separate integration for every manual operation.

But exposing more operations does not automatically make the model more effective. Ahuja reports repeatedly refactoring an integration that had roughly 14 or 15 tools because tool selection became confused. The problem was deciding which capability to use for a request.

His examples show why the choices can overlap:

| Exposed capability | Route to a result |
| --- | --- |
| Create a cube or sphere | Request a primitive shape directly. |
| Execute code | Use a script to construct scene content, including primitive shapes. |
| Retrieve an asset from Rodin | Obtain a generated asset rather than construct it directly. |

A request for a simple shape can fit both a dedicated creation tool and general code execution. The model has to choose between routes that may lead to the same visible result.

Ahuja’s response is to keep the interface lean and make each capability clearly distinguishable. **Distinct responsibilities make tool selection easier.** The useful lesson is to reduce ambiguity between operations, rather than adopt his tool count as a universal limit.

That principle carries into the product experience. An open-source project can attract many feature requests, but adding every possible feature can erode the lean, general-purpose workflow that made it useful.

Meanwhile, the underlying models improve. Ahuja still finds their understanding of 3D limited, but points to **Gemini 2.5** as an example of progress he noticed during the project’s development. A broadly useful scripting bridge can benefit from that progress without needing a new dedicated feature for every kind of scene.

### Generated assets, animation, and image references

[7:44](https://www.youtube.com/watch?v=nnktgWtfJHE&t=464s)

Once other people started using the bridge, its possibilities became more concrete. Ahuja begins the showcase with his own scene assembled from newly generated assets, including a magical mushroom. He describes the objects he wants, tells Claude where to place them, and captures the resulting composition.

Ahuja reports making the magical-mushroom scene in two minutes. He emphasizes that the assets were generated for the scene: prompting covers both obtaining the objects and arranging them, rather than only positioning a collection he already had.

A separate cat example adds another operation. Its creator obtains generated assets and then animates them a little, giving the scene a sense of life. Ahuja says the cat workflow can be completed in less than an hour. The result is no longer just a composition to photograph; its objects can move.

The next example changes the input. A creator supplies an image of a living room, and the model uses that reference to guide reconstruction and obtain appropriate assets. Ahuja describes the living-room reconstruction as taking minutes.

A reference image gives the workflow a visual target. Instead of describing every object and spatial relationship in words, the creator can show the arrangement they want the scene to resemble.

### Terrain nodes, game scenes, and animated materials

[9:04](https://www.youtube.com/watch?v=nnktgWtfJHE&t=544s)

Another creator works in Cursor with an image reference to generate terrain in Blender. This reaches into a more specialized part of the application: **nodes** that configure textures and surface bump or normal detail.

Those node arrangements have their own learning curve. Because Blender can execute code, the model can configure them as part of creating the requested terrain. The scripting bridge reaches beyond placing objects into the machinery that determines how their surfaces look.

Ahuja is particularly delighted by the next game’s unusual premise: the player enters someone’s lungs, collects bone fragments, and reconstructs a rib cage to win. Blender MCP was used to set up the scene and create assets. Its contribution here is the environment and objects that support the game’s peculiar objective.

A further showcase focuses on a glossy, iridescent material and an animated camera. Ahuja says this material and camera animation were produced through prompting in minutes. The request now reaches beyond an object’s shape into its surface appearance and the camera movement used to present it.

### A Blender racing scene becomes a Runway clip

[10:30](https://www.youtube.com/watch?v=nnktgWtfJHE&t=630s)

The racing example begins with a prompt to create a track and animate cars. The Blender scene contains a circular racetrack, cars, colored obstacles, trees, and stands. The creator then places the camera so the racing action starts to feel like a movie shot. This is a constructed 3D scene whose objects and framing can be directed before the next production step.

![The constructed racing scene supplies visual material for the next video-generation step.](https://ai.engineer/api/talk-essay-media/8acee0db9c2010557d7dbee2a105bf01f81cfe19f43753797f4026151c3c1e6b)

The constructed racing scene supplies visual material for the next video-generation step.

The creator also animates the camera, then uses Runway to transform the Blender-derived material into the final displayed clip. **Blender establishes the scene and motion; Runway produces the transformed footage.**

That division opens the workflow to filmmakers as well as 3D artists. A controllable scene can become an intermediate step in making a shot, even when the Blender render is not the final visual medium. The track, cars, and camera movement supply structure for the subsequent video-generation work.

### Returning to the donut

[11:27](https://www.youtube.com/watch?v=nnktgWtfJHE&t=687s)

Ahuja returns to the opening exercise with donuts made from a short prompt. Ahuja estimates about a minute for the prompted donut example. He also acknowledges that the result could be much better.

The contrast with his five-hour beginner course concerns the route to a starting result. Following a tutorial teaches operations; prompting produces something to inspect and refine. They do not establish equal quality or equal skill acquisition, but the prompted example changes what a newcomer can attempt before mastering the interface. A simple idea can now become a visible object that gives the next prompt something concrete to work on.

### A workflow organized around creator intent

[12:03](https://www.youtube.com/watch?v=nnktgWtfJHE&t=723s)

Ahuja then extends orchestration beyond Blender. If a model application can coordinate a local creative tool and external asset services, it could also coordinate several creative applications.

The organizing principle is **creator intent**. People come to Unity because they want to make a game, and to Ableton because they want to make music. Learning the software is a means to that outcome. The challenge is to capture what someone wants to create and translate it into work across applications while still matching their vision. Ahuja sees MCP connecting those tools, with the language model interpreting the request and coordinating the work.

In his proposed game workflow, the user describes the game to the model application. The application would coordinate several responsibilities:

- **Blender:** Create the assets needed for the game.
- **Unity:** Assemble the game, add collisions, and implement its logic.
- **External services:** Supply additional assets or animation.
- **Ableton:** Create music for the characters and game.

This is an envisioned production chain. The creator would direct one project while the application chooses which underlying tool should perform each part.

### A dragon and its soundtrack

[14:04](https://www.youtube.com/watch?v=nnktgWtfJHE&t=844s)

To demonstrate a smaller version of that idea, Ahuja combines Blender MCP with his companion project, [Ableton MCP](https://github.com/ahujasid/ableton-mcp). The request is to create a dragon and give it a soundtrack. Ableton MCP supplies the connection through which the model application can request music creation, alongside its existing connection to Blender.

The result has two coordinated parts. Blender contains the described dragon, with sinister lighting appropriate to a villain. Ableton creates the soundtrack. The character brief influences both the visual scene and the music, while each application produces its own output.

Ahuja is candid that the quality is still limited. What excites him is the ability to stitch the pieces together: one creative request can guide work that would otherwise require separate operations in two very different interfaces.

### What creators still need to direct

[15:15](https://www.youtube.com/watch?v=nnktgWtfJHE&t=915s)

These experiments leave Ahuja with a question about interfaces: will more people work primarily through a model application, without learning every complex tool beneath it? He sees new creators entering that way already.

His analogy is an **orchestra conductor**. The creator needs to articulate the intended result and coordinate its parts, even when they do not personally operate every instrument. Expressing a vision clearly becomes central to making it executable: which pieces belong together, what each should contribute, and how the result should feel.

Blender MCP and Ableton MCP are his concrete examples, but Ahuja also reports seeing integrations for PostGIS, Houdini, Unity, and Unreal Engine. He expects that expanding set of connections to let more people create across media. His enthusiasm rests on the possibility that someone with a clear idea could direct the necessary tools before becoming an expert in each one.

## Resources

- [Blender MCP](https://github.com/ahujasid/blender-mcp) — The speaker's bridge from an LLM client to Blender's scripting and scene tools.
- [Ableton MCP](https://github.com/ahujasid/ableton-mcp) — The second creative tool used to add a soundtrack to the closing dragon demonstration.
- [Current MCP architecture](https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture) — Current host/client/server vocabulary; protocol examples in this version postdate the talk.

## Slides

### Blender MCP

Siddharth Ahuja introduces his experience building Blender MCP and where he sees creative tools going. The title slide shows a frog and cat beneath a giant mushroom.

[0:00](https://www.youtube.com/watch?v=nnktgWtfJHE&t=0s) [Title slide for a talk on Blender MCP and creative tools, with a fantasy scene featuring a frog and a cat.](https://assets.ai.engineer/sites/aiecode2025/sha256/29892b543cf3f52efc518e1f17146f1bd2804cb967b33fe56fc8439f5185b50f.webp)

BLENDER MCP

AI ENGINEER’S
WORLD FAIR

MCPS AND
CREATIVE TOOLS

### Blender interface

Blender’s default scene sits amid tabs and controls across the top and right. Ahuja found the interface complex and wondered whether MCP could make Blender easier to use.

[0:54](https://www.youtube.com/watch?v=nnktgWtfJHE&t=54s) [Blender's interface with the default cube selected in the 3D viewport.](https://assets.ai.engineer/sites/aiecode2025/sha256/27235221bd49df27841823e281ee042c04204ea6fa95401622a4c1eb35d5e322.webp)

Interface text:
File  Edit  Render  Window  Help
Layout  Modeling  Sculpting  UV Editing  Texture Paint  Shading  Animation  Rendering  Compositing  Geometry Nodes  Scripting
Scene  ViewLayer
Object Mode  View  Select  Add  Object  Global
Waiting for Client
Options
User Perspective
(1) Collection | Cube
Scene Collection
Collection
Camera
Cube
Light
Cube
Transform
Location X 0 m
Y 0 m
Z 0 m
Rotation X 0°
Y 0°
Z 0°
Mode XYZ Euler
Scale X 1.000
Y 1.000
Z 1.000
Delta Transform
Relations
Support the authors by subscribing to Full plan.
Playback  Keying  View  Marker
1  Start

### Beginner Blender tutorial

Ahuja points to Blender Guru’s nearly five-hour donut course as an example of Blender’s learning curve and his motivation for letting an LLM control Blender through prompts.

[1:40](https://www.youtube.com/watch?v=nnktgWtfJHE&t=100s) [A beginner Blender course card shows a plain donut progressing to a pink frosted donut.](https://assets.ai.engineer/sites/aiecode2025/sha256/83ddc655d1f4d9ab93ec6231c87fa155459ff9c661bd2ff26f447668ee1ffeeb.webp)

FULL COURSE

Beginner Blender Tutorial - Full Course
1.6M views · 10 months ago
Blender Guru

The complete beginner blender donut tutorial course in one vide[illegible]

95 chapters  Intro | Download and Install | Interfac[illegible]

4:55:04

### Dragon and pot of gold

The demo shows a winged green dragon beside a pot of gold in a lit isometric room. Ahuja says it took about five minutes and only partly met the brief.

[2:43](https://www.youtube.com/watch?v=nnktgWtfJHE&t=163s) [A Blender scene shows a green dragon beside a pot of gold in a lit isometric room.](https://assets.ai.engineer/sites/aiecode2025/sha256/0cc1489e7c2308540c12bfa7fb80babbe99fd9b0efc407733a1434ab9c450733.webp)

Interface text:
[illegible]her inside the pot, spilling[illegible]
[illegible]etallic appearance. This cr[illegible]
[illegible]ly from the fires in the dun[illegible]
[illegible]s atmospheric quality whi[illegible]
[illegible]now are simple rectangles,[illegible]
[illegible]more definition:
[illegible]er_code from BlenderMCP (loc[illegible]
[illegible]more definition by transf[illegible]
[illegible]red, bat-like wings:
[illegible]nes:
[illegible]branes instead of flat recta[illegible]
[illegible]d along the top edge
[illegible]red appearance toward the[illegible]
[illegible]dge to curve inward like re[illegible]
[illegible]ents:
[illegible]ne" along the top edge of ea[illegible]
[illegible]bones radiating outward t[illegible]
[illegible]ecrease in length toward th[illegible]
[illegible]cture
[illegible]uggest the skeletal framew[illegible]
Collection
DragonWi[illegible]
Transform
Location X Y Z
Rotation X Y Z
Mode
Scale X Y Z
Delta Tra[illegible]

[2:46](https://www.youtube.com/watch?v=nnktgWtfJHE&t=166s) [A Blender scene shows a green dragon beside a glowing pot of gold in a torchlit room.](https://assets.ai.engineer/sites/aiecode2025/sha256/6987d8d1b3d4495c7ad3b712d5f6a3c62830ad495dc3c8612a934346af506c8f.webp)

Interface text:
[illegible]her inside the pot, spilling[illegible]
[illegible]etallic appearance. This cr[illegible]
[illegible]ly from the fires in the dun[illegible]
[illegible]s atmospheric quality whi[illegible]
[illegible]now are simple rectangles,[illegible]
[illegible]more definition:
[illegible]er_code from BlenderMCP (loc[illegible]
[illegible]more definition by transf[illegible]
[illegible]red, bat-like wings:
[illegible]nes:
[illegible]branes instead of flat recta[illegible]
[illegible]d along the top edge
[illegible]red appearance toward the[illegible]
[illegible]dge to curve inward like re[illegible]
[illegible]ents:
[illegible]ne" along the top edge of ea[illegible]
[illegible]bones radiating outward t[illegible]
[illegible]ecrease in length toward th[illegible]
[illegible]cture
Collection
DragonWi[illegible]
Transform
Location X Y Z
Rotation X Y Z
Mode
Scale X Y Z
Delta Tra[illegible]
0:22 / 0:22

### GitHub stars and downloads

At the time of the talk, Blender MCP had 11.4K GitHub stars and 160K+ downloads. Ahuja says people have also built on top of it.

[3:05](https://www.youtube.com/watch?v=nnktgWtfJHE&t=185s) [Yellow slide showing 11.4K GitHub stars and 160K+ downloads.](https://assets.ai.engineer/sites/aiecode2025/sha256/90486d7727841dbc396756f690b0f0efb406903733a767c73288fcf8dd17121d.webp)

11.4K
STARS ON GITHUB

160K+
DOWNLOADS

### How it works

Ahuja introduces how Blender MCP works.

[3:23](https://www.youtube.com/watch?v=nnktgWtfJHE&t=203s) [Pink slide titled How it works.](https://assets.ai.engineer/sites/aiecode2025/sha256/ac47acb7ecb89091e18f9d94f822e386dd7bdbc7eb6af99d5fe166e6f19fb97d.webp)

HOW IT
WORKS

### Learnings

Ahuja found that Blender could execute model-written scripts, but around 14 or 15 tools confused selection. He recommends a lean UX and expects underlying models to improve.

[5:49](https://www.youtube.com/watch?v=nnktgWtfJHE&t=349s) [Four lessons: use scripting to reduce heavy lifting, keep tools lean, avoid bloating UX, and trust underlying models to improve.](https://assets.ai.engineer/sites/aiecode2025/sha256/e62a1dd42d3f0b6349d346467326784b8d1e49a228b58253e5a5c42ecee4478e.webp)

LEARNINGS

1. A tool with scripting can remove a lot of heavy lifting
2. MCP gets confused with tools, keep it lean
3. Don’t bloat UX just because you can
4. Trust the underlying models will get better

### What people use it for

Ahuja turns to how people use Blender MCP as the barrier to using 3D tools falls.

[7:54](https://www.youtube.com/watch?v=nnktgWtfJHE&t=474s) [Tan slide titled What people use it for.](https://assets.ai.engineer/sites/aiecode2025/sha256/15ec31f26806ee0fbbf1f66cc5092e949927cded029d083ef98b02753412ac62.webp)

WHAT
PEOPLE
USE IT FOR

### Animated cat scene

A white cat rests on a green sofa in a colorful room. The creators used AI-generated assets and added animation; Ahuja says the scene can now be made in less than an hour.

[8:37](https://www.youtube.com/watch?v=nnktgWtfJHE&t=517s) [A white cat rests on a green sofa in a colorful room.](https://assets.ai.engineer/sites/aiecode2025/sha256/3f79801ba9977021c7bd0192c201e629309bb78cb0970296f8856fa07dc460be.webp)

Interface text:
0:12 / 0:12

### Living room modeling

A living-room reference is recreated with assets; the demo shows a furnished Blender scene beside a simpler room model. Ahuja says the process takes minutes.

[8:59](https://www.youtube.com/watch?v=nnktgWtfJHE&t=539s) [Two Blender views show a furnished room and a simpler room model, labeled Blender-MCP and HYPER3D Rodin.](https://assets.ai.engineer/sites/aiecode2025/sha256/75138e90babc62673ed67be0fae284a376eb9902c6c232d9e8157c0c2b8c4786.webp)

Blender-MCP
+ HYPER3D Rodin

wit[illegible]

Interface text:
0:14 / 0:14

### Terrain reference

A desert reference image sits beside an empty Blender plane as a user tries to generate terrain with Blender MCP in Cursor. The chat shows attempts to inspect the scene’s node tree.

[9:06](https://www.youtube.com/watch?v=nnktgWtfJHE&t=546s) [A desert reference image appears beside a mostly empty Blender scene.](https://assets.ai.engineer/sites/aiecode2025/sha256/8f0aa26cc5b77a5683af1d3a1b72243c628a4ec5d39c6356249fa911859bfd50.webp)

Let me make one more attempt to get the node values with a different approach:
Called MCP tool execute_blender_code
I'll try a different approach to understand the current structure of the node tree:

Interface text:
iStocknemchinowa-1142542838.jpg
User Perspective
(1) Collection | Plane
Rendering Done
File  Edit  Render  Window  Help
Layout  Modeling  Sculpting  UV Editing  Texture Paint  Shading  Animation  Rendering  Compositing  Geometry Nodes
Object Mode  View  Select  Add  Object
Orientation: Default  Drag: Select Box  Options
Chat
Generating...
Add context
Plan, search, build anything
Agent  claude-3.7-sonnet
Playback  Keying  View  Marker

### Racing scene

A red race car rounds a colorful track. The creator animated the camera and used Runway to turn the scene into a clip.

[11:05](https://www.youtube.com/watch?v=nnktgWtfJHE&t=665s) [A red race car travels along a colorful track lined with trees and spheres.](https://assets.ai.engineer/sites/aiecode2025/sha256/b2769973e5890a173f349c8dae7fa9001aff56dbe70ce49aeff971263cc74ee0.webp)

Interface text:
0:29 / 0:41

### Donut modeling example

Ahuja shows two pink-frosted 3D donuts, one with a coffee cup. He says the example took one short prompt and about a minute, and could be improved.

[11:25](https://www.youtube.com/watch?v=nnktgWtfJHE&t=685s) [Two views of a pink-frosted 3D donut, one beside a coffee cup.](https://assets.ai.engineer/sites/aiecode2025/sha256/1e106c7a6556d46f675c9f6a1cb8d1a74a2c98ff8af9689f905984fde56a7e84.webp)

### MCPs are changing how creative tools work

Ahuja proposes extending the client’s role as an orchestrator between local tools like Blender and external sources such as APIs.

[12:01](https://www.youtube.com/watch?v=nnktgWtfJHE&t=721s) [Yellow slide stating that MCPs are changing how creative tools work.](https://assets.ai.engineer/sites/aiecode2025/sha256/a47ea10fc257bd7dca2de48260a189641042bbce471f941c1e0f97719e98fff8.webp)

MCPS ARE CHANGING HOW
CREATIVE TOOLS WORK

### Client as orchestrator

Ahuja imagines a client turning “make a game” into coordinated work: Blender creates assets, Unity builds the game, Ableton makes the soundtrack, and APIs supply additional assets.

[12:30](https://www.youtube.com/watch?v=nnktgWtfJHE&t=750s) [A client connects to Blender, Ableton and Unity through MCP and to APIs through an API.](https://assets.ai.engineer/sites/aiecode2025/sha256/340265ac75c2b8fd46dfa6063063ea8e4ce34f6bc9a64821c78681b2606ad127.webp)

“MAKE A GAME”

ABLETON
MCP

ORCHESTRATOR
BLENDER ↔ MCP ↔ CLIENT ↔ MCP ↔ UNITY

API
APIS

### Creative tools demo setup

Ahuja combines Blender and Ableton in a demo to create a dragon and give it a soundtrack. He built the Ableton MCP to let users prompt it to create music.

[14:11](https://www.youtube.com/watch?v=nnktgWtfJHE&t=851s) [A chat client, Ableton and Blender are displayed together, with the Blender MCP panel open.](https://assets.ai.engineer/sites/aiecode2025/sha256/c7fcb7649c06d1831495631645440ed6624e5160c4fd6ab335d5dd653dfd38ab.webp)

Interface text:
Hey there, ahujasid
How can I help you today?
29
Claude 3.7 Sonnet

Blender MCP
Port 9876
Use assets from Poly Haven
Use Hyper3D Rodin 3D model generati...
Rodin M... hyper3d.ai
API Key: [redacted]
Set Free Trial API Key
Disconnect from MCP server
Running on port 9876

Object Mode
View  Select  Add  Object
User Perspective
(1) Collection | Cube

Link  Tap  120.00  4 / 4  1 Bar  C  Major  1.1.1
1 MIDI
2 MIDI
3 Audio
4 Audio
A Reverb
B Delay
Drop Files and Devices Here
Sends
Post
Solo
Drop an Instrument or Sample Here

### Dragon creation prompt

Ahuja prompts Claude to create a villainous dragon in Blender, as part of a demo combining Blender with an Ableton-generated soundtrack.

[14:28](https://www.youtube.com/watch?v=nnktgWtfJHE&t=868s) [A chat prompt requests a villainous dragon in Blender.](https://assets.ai.engineer/sites/aiecode2025/sha256/1d0aa2a5e9e23cdc1f31d7ab4fa27a6dba4a767d7f89a03d11684dbc2334ec8d.webp)

Create a villanous looking dragon in Blender.

Interface text:
Hey there, ahujasid
29
Claude 3.7 Sonnet
Untitled
Link
Tap
120.00
4 / 4
1 Bar
C
Major
1.1.1
1 MIDI
2 MIDI
3 Audio
4 Audio
A Reverb

### Dragon and soundtrack demo

The demo combines a villainous dragon and dramatic lighting in Blender with a soundtrack created in Ableton. The Ableton tracks appear alongside the finished dragon.

[14:38](https://www.youtube.com/watch?v=nnktgWtfJHE&t=878s) [Ableton music tracks appear beside a lit 3D dragon in Blender.](https://assets.ai.engineer/sites/aiecode2025/sha256/469a650df7c4e99d7564e5284d67861dfccd7e07dcec7ce7254380754bb6ec5a.webp)

Interface text:
2 MIDI
3 Drama Synth
DarkStrings
DarkBrass
DragonPercussio[illegible]
A Reverb
B Delay
Main

Atmospheric S[illegible]
Ominous Brass
Dragon Bass
Dragon Heart[illegible]

1
2
3
4
5
6
7
8

MIDI From
All Ins
All Channels
Monitor
In  Auto  Off
MIDI To
No Output
Audio To
Main
Cue Out
1/2
Main Out
1/2
Sends
Post
Solo

-12.8
-8.91
-0.58
0.80

Moody Fanfare
Rand
Map
Low Pass Filter
Hi Pass Filter
Drift
Shape
1.41 kHz
677 Hz
52%
0.70
Attack
Release
Spread
Reverb
Drop Audio Effects Here

(1) Collection | Backdrop

## Full transcript

[0:01](https://www.youtube.com/watch?v=nnktgWtfJHE&t=1s) Hey everyone, this is Siddharth. Welcome to my talk about the Blender MCP. Uh, for those of you who don't know what Blender is or MCP is, I'm going to go through it in a bit.

[0:09](https://www.youtube.com/watch?v=nnktgWtfJHE&t=9s) But I'm gonna talk about how my experience was building this, what I learned, and where I see it going forward, uh, especially for more creative tools even outside of Blender.

[0:20](https://www.youtube.com/watch?v=nnktgWtfJHE&t=20s) So maybe a little bit about me before we start. I've been a designer and an engineer for about eight years now. I just like tinkering with stuff. I ran my own product studio for a while, and this Blender MCP was a result of some experimentation.

[0:35](https://www.youtube.com/watch?v=nnktgWtfJHE&t=35s) Um, just... but just before we jump into it, you know, a lot of you might be asking: What is Blender? So Blender is just a 3D tool. Think of it as a generalist 3D tool.

[0:44](https://www.youtube.com/watch?v=nnktgWtfJHE&t=44s) You can import assets, you can animate them, you can export them out to like a game engine, so you can do all sorts of stuff in Blender. You can create art, right?

[0:54](https://www.youtube.com/watch?v=nnktgWtfJHE&t=54s) And the UI kind of looks like this. It's pretty complex if you see all the different tabs everywhere. Uh, on the top over here, there's a bunch of things.

[1:03](https://www.youtube.com/watch?v=nnktgWtfJHE&t=63s) On the right over here, there's a bunch of things. Each of these has like 10 tabs inside it. So it gets pretty complex, which is the reason I myself could never be a good 3D artist. [chuckles]

[1:14](https://www.youtube.com/watch?v=nnktgWtfJHE&t=74s) I was too lazy to go through all of these different tabs. And, uh, uh, I, I guess that was kind of my motivation when I saw MCP and, uh, I saw that MCP could let your LLM talk to any tool.

[1:28](https://www.youtube.com/watch?v=nnktgWtfJHE&t=88s) My first response was, "Oh, wait, will this make Blender easier?" You know, will this make a historically complex tool easy to use? And so just to give you an idea of how it used to be or even still is, it takes five hours to build this donut, and this is a very classic beginner's course that even I

[1:47](https://www.youtube.com/watch?v=nnktgWtfJHE&t=107s) did. But, uh, th- this is the status quo, right? It takes five hours to go through this and build a donut, and it should not be this hard, right?

[1:57](https://www.youtube.com/watch?v=nnktgWtfJHE&t=117s) And so the whole idea behind Blender MCP, uh, is, is essentially to let your LLM, like Claude or ChatGPT or whatever, right? Let them talk to Blender, which is a complex tool, and let the LLM control Blender so that it can make 3D scenes for you, and you just have to prompt.

[2:15](https://www.youtube.com/watch?v=nnktgWtfJHE&t=135s) So in this example, this is a demo I posted. Essentially, I'm just saying, "Make a dragon," right? "Have it guard a pot of gold," and let's see what it does.

[2:44](https://www.youtube.com/watch?v=nnktgWtfJHE&t=164s) Right. So you can see it kind of gets the brief, [chuckles] but also not the best. But it, it made an isometric room. It has a dragon. It kind of gave it wings.

[2:53](https://www.youtube.com/watch?v=nnktgWtfJHE&t=173s) There's a pot of gold. It, it made it in what? I think about five minutes. I would have taken a lot longer to do something like this, to be honest.

[3:03](https://www.youtube.com/watch?v=nnktgWtfJHE&t=183s) Uh, so this is, this is where I think I'm gonna talk about a little bit more. So Blender MCP launched to about 11 and a half thousand stars on GitHub at this moment.

[3:13](https://www.youtube.com/watch?v=nnktgWtfJHE&t=193s) Uh, and it has almost, I think, way more than 160k plus downloads. A lot of people have used it. A lot of people have built on top of it, and I'll show some examples in a bit.

[3:25](https://www.youtube.com/watch?v=nnktgWtfJHE&t=205s) But how, how does it work exactly, right? So it's actually way more straightforward [chuckles] than it seems.

[3:32](https://www.youtube.com/watch?v=nnktgWtfJHE&t=212s) So it's just essentially your client, which is Claude or Cursor or whatever, it connects to Blender through the MCP protocol, right? If you haven't seen what an MCP is, I feel like a lot of people are...

[3:45](https://www.youtube.com/watch?v=nnktgWtfJHE&t=225s) have been talking about it even in this conference itself. But it helps you. It's just a standardized protocol that allows Blender to show to the client, "Oh, this is what I can do."

[3:56](https://www.youtube.com/watch?v=nnktgWtfJHE&t=236s) Like, so that's the tools part of the MCP that, "Oh, these are the tools I have, and this is what I can do." And so the LLM understands that and then uses those tools.

[4:04](https://www.youtube.com/watch?v=nnktgWtfJHE&t=244s) So how it uses those tools is in Blender, there's an add-on that I've made, uh, to execute the scripts that the LLM tells it to. So for example, Claude will say, "Make a dragon," and it will call the exact right tools to make those...

[4:19](https://www.youtube.com/watch?v=nnktgWtfJHE&t=259s) make that dragon in Blender. Another big part of it is the assets, right? So the industry standard like Rodin, which is an AI-generated asset, Sketchfab and Poly Haven, things like that are now connected to the LLM, and that can basically now seamlessly, if you write a prompt to generate an asset inside Blender, it can just do that,

[4:39](https://www.youtube.com/watch?v=nnktgWtfJHE&t=279s) right? So the client does all the heavy lifting, essentially. Yeah. So I think Blender is a pretty big part. I think this reason this is possible in the first place is because Blender has scripting, right?

[4:50](https://www.youtube.com/watch?v=nnktgWtfJHE&t=290s) So code can be executed inside Blender, which is a big part. Blender is pretty flexible with also downloading assets and importing, and so that makes the life like much easier, honestly.

[5:02](https://www.youtube.com/watch?v=nnktgWtfJHE&t=302s) With assets, yeah, I think the cool thing here is that this is just the start, but clients can connect to any API. So for example, right now, you can write any prompt you want, and it will get the right asset for you.

[5:14](https://www.youtube.com/watch?v=nnktgWtfJHE&t=314s) You can say, "I want a zombie," and it'll get the right asset for you, AI-generated on the spot. You can describe it however you want. And then the client is kind of the orchestrator, right?

[5:25](https://www.youtube.com/watch?v=nnktgWtfJHE&t=325s) So the cool thing about this is I think that you can use it in any tool you want. You know, it could be Claude, it could be Cursor, it could be Windsurf, LangChain, whatever you like.

[5:35](https://www.youtube.com/watch?v=nnktgWtfJHE&t=335s) Uh, and you can use any language model you want with it, right? You can use, uh, uh, Claude and ChatGPT and Gemini and whatever you like. So I think this is how it broadly functions together.

[5:47](https://www.youtube.com/watch?v=nnktgWtfJHE&t=347s) If you want more detail, there's al- always the GitHub. But, uh, I think some learnings while I was making this was that a tool with scripting can remove a lot of the heavy lifting.

[5:58](https://www.youtube.com/watch?v=nnktgWtfJHE&t=358s) Like I mentioned, the Blender thing, right? Because Claude is good at writing code, it can very easily translate it to Blender, and Blender can execute that code. And that can be for modeling, for getting the right assets, anything.

[6:12](https://www.youtube.com/watch?v=nnktgWtfJHE&t=372s) Um, the second part I learned was that MCPs get really confused with tools. So, uh, I learned this the hard way where, where I had to refactor the Blender MCP quite a few times because I had about, I think, 14 or 15 tools, and it kept getting confused on what to use.

[6:28](https://www.youtube.com/watch?v=nnktgWtfJHE&t=388s) So tools can be something like create a cube, create a sphere, execute code, uh, get this asset from Rodin, for example, right? So how does it know which one to choose?

[6:39](https://www.youtube.com/watch?v=nnktgWtfJHE&t=399s) Because it's a little bit non-deterministic, right? So in that case, it's always better to kind of keep the end user experience in mind and making sure it's really lean and every single tool is different from each other so that Claude knows exactly which tool to pick.

[6:56](https://www.youtube.com/watch?v=nnktgWtfJHE&t=416s) Um, and a good segue from that is don't bloat the UX just because you can. I think this is more a learning from making it open source, which is just be-- I think there's a lot of features that can be added, but I think the reason Blender MCP works is because lean and a bit of a generalist

[7:13](https://www.youtube.com/watch?v=nnktgWtfJHE&t=433s) tool, so it can get a lot done. And another learning has been that the models do get better, the underlying models. So while 3D models aren't great yet, and LLMs have a very poor understanding of 3D in general, they're getting way better.

[7:28](https://www.youtube.com/watch?v=nnktgWtfJHE&t=448s) So even in the time I released it to the time it was out, Gemini 2.5 came out, and that made it already 3X better, right? So I think those are some things to keep in mind when I'm building at least the next MCP.

[7:44](https://www.youtube.com/watch?v=nnktgWtfJHE&t=464s) Now, sure, now I've put this out in the wild, and now comes the creative tools part, right? What's, what's changed? Uh, how are people using it? So historically, like I said, it's been pretty complex to use 3D tools, and now suddenly the barrier of access has reduced.

[8:04](https://www.youtube.com/watch?v=nnktgWtfJHE&t=484s) And so this is a scene I made in two minutes [chuckles], you know, just got the right a-assets. AI generated all of them. These assets don't exist otherwise. They're all AI generated and just place them, tell Claude how to place it, tell them, "I need a magical mushroom," and it just creates everything from scratch, and I can

[8:20](https://www.youtube.com/watch?v=nnktgWtfJHE&t=500s) just take a picture of it, essentially. This is, uh [upbeat music] another one.

[8:29](https://www.youtube.com/watch?v=nnktgWtfJHE&t=509s) Where... This is another one where they're creating a cat, and they're also getting all the right AI generated assets, and then they animated it a little bit to make it feel real.

[8:39](https://www.youtube.com/watch?v=nnktgWtfJHE&t=519s) And you can do all this in less than an hour now, where this would have taken way more time earlier, right? This is another one [upbeat music]

[8:48](https://www.youtube.com/watch?v=nnktgWtfJHE&t=528s) where, where they're providing reference images, right? So they just gave an image of a living room, and now it's recreating that, getting all the right assets. Again, this would have taken quite a long time earlier to just make this, but now it's a matter of minutes.

[9:04](https://www.youtube.com/watch?v=nnktgWtfJHE&t=544s) Some other cool things. This person, uh, on Twitter, they're generating terrain. So they have an image which they gave to the Blender MCP, uh, and inside Cursor, they're trying to create, create this game on Blender.

[9:16](https://www.youtube.com/watch?v=nnktgWtfJHE&t=556s) And so it generates the right terrain for you. It even uses these nodes, right? Which is, which it itself has a learning curve to set up these really complex textures and normal bumps and so on.

[9:29](https://www.youtube.com/watch?v=nnktgWtfJHE&t=569s) And so it does that, all of that for you just because Blender can execute code, right?

[9:34](https://www.youtube.com/watch?v=nnktgWtfJHE&t=574s) This is... I love this one. This is [upbeat music] a game that someone created. This is essentially...

[9:41](https://www.youtube.com/watch?v=nnktgWtfJHE&t=581s) The idea is that they go into someone's lungs, and they have to collect bone fragments, um [chuckles], to, to win the game, to connect the rib cage together. And so Blender MCP, again, was used to set the scene to create assets.

[9:53](https://www.youtube.com/watch?v=nnktgWtfJHE&t=593s) I'll, I'll just play it shortly. [upbeat music] Yeah.

[10:12](https://www.youtube.com/watch?v=nnktgWtfJHE&t=612s) I'll just leave it at that. Um, so you can create games now [chuckles]. And this is, uh, completely done in Blender MCP. It's a pretty high fidelity of, you know, glossy, this iridescent material and a camera animation all done in minutes by just prompting through AI, right?

[10:30](https://www.youtube.com/watch?v=nnktgWtfJHE&t=630s) Uh, so these are the things that are being unlocked. Um, this is, uh, another cool thing that I saw that people have been using it for. So this person prompted the MCP to create a racing track and then animate the cars.

[10:43](https://www.youtube.com/watch?v=nnktgWtfJHE&t=643s) So you can see on the side the MCP is running and, um, on the right side, this Blender is running essentially. And so this person created this, and now you can see if I skip to the end a little bit, this person now placed the camera angle such that the cars feel like they're [chuckles], feel like a

[11:04](https://www.youtube.com/watch?v=nnktgWtfJHE&t=664s) movie, and then they used Runway to convert them to an actual clip. So here, here you can see it. Whoops.

[11:13](https://www.youtube.com/watch?v=nnktgWtfJHE&t=673s) Yeah, there you go. Yeah. So they animated the camera, and now this is through Runway. So it's another medium that's been unlocked, basically, where you're... Even filmmakers or creators, all kinds of creators can use this, not just 3D artists.

[11:27](https://www.youtube.com/watch?v=nnktgWtfJHE&t=687s) And this is ju- [chuckles] just an example of some donuts, which are one short prompt. This is just, you know, like in a minute. Uh, it can be ma- maybe, uh, made way better, of course.

[11:39](https://www.youtube.com/watch?v=nnktgWtfJHE&t=699s) But, uh, you know, as a start from five hours to a minute is not too bad. So this is essentially unlocking a whole new

[11:49](https://www.youtube.com/watch?v=nnktgWtfJHE&t=709s) world of creators to just come in, and when the barrier has been so high, now it's just gone, and you can just write what you want, what's in your head, and get there with just enough prompting, right?

[12:03](https://www.youtube.com/watch?v=nnktgWtfJHE&t=723s) And so I think in general, in a broader sense, MCPs are changing how creative tools work. And, um, just an example of that, I was trying to experiment with this a little bit.

[12:14](https://www.youtube.com/watch?v=nnktgWtfJHE&t=734s) We were talking about The client, right, being the orchestrator where it talks to external sources like the API, it talks to local tools like Blender. So what if we extend that anal-analogy a little bit and the client orchestrates between all these different things?

[12:35](https://www.youtube.com/watch?v=nnktgWtfJHE&t=755s) So let's say the user wants to make a game, and people don't come in with the intent of learning Unity, right? They want to make a game, and people don't come in with the intent of learning Ableton, which is a music creation software.

[12:47](https://www.youtube.com/watch?v=nnktgWtfJHE&t=767s) They come in with the intent of making music. So how do we capture that intent and then transform it so that this person doesn't have to worry about the underlying tools, but also it can match their vision?

[13:01](https://www.youtube.com/watch?v=nnktgWtfJHE&t=781s) So I feel like MCPs are going to be a fundamental glue that holds this thing together, and these LLMs are going to be at the center, at the intelligence, uh, at the center of it, right?

[13:13](https://www.youtube.com/watch?v=nnktgWtfJHE&t=793s) So for example, let's say I want to make a game. So I tell it, "Oh, I wanna make a game," and, uh, this, this LLM is all they interface with, right?

[13:24](https://www.youtube.com/watch?v=nnktgWtfJHE&t=804s) And this LLM can then call Blender and make an asset for the game, the right assets. It can then call Unity and make a whole game. Unity is a game engine, and so it can put it in, add collisions, add logic, and make a whole game out of it.

[13:37](https://www.youtube.com/watch?v=nnktgWtfJHE&t=817s) It can call the right APIs to get the right assets and animate it and stuff like that. And it can also call Ableton, which will create the soundtrack for the characters, for the game, right?

[13:49](https://www.youtube.com/watch?v=nnktgWtfJHE&t=829s) So you-- this person doesn't really care about everything outside of it. But now that MCP exists, the client can literally just orchestrate between all of these and, uh, choose the right tools and make a game.

[14:04](https://www.youtube.com/watch?v=nnktgWtfJHE&t=844s) So I don't think we're very far away from this, to be honest. And, uh, I made like a really short demo to demonstrate how it could work. So in this one, I'm creating a dragon, and I'm just asking it to give a soundtrack.

[14:19](https://www.youtube.com/watch?v=nnktgWtfJHE&t=859s) So I also created the Ableton MCP, which is what you see on the bottom left, which essentially you can prompt to create music. So I thought, let's try and combine them and see what happens. [electronic music]

[14:51](https://www.youtube.com/watch?v=nnktgWtfJHE&t=891s) So you can see that it creates-- it gets the dragon that I described. It creates some sinister lighting because it's supposed to be a villain, and it also calls Ableton to create a soundtrack for it.

[15:03](https://www.youtube.com/watch?v=nnktgWtfJHE&t=903s) Sure, the quality might not be the best in the world right now, but at the same time, it's-- you can see it's only a matter of time before it starts stitching all these pieces together to create something insane.

[15:15](https://www.youtube.com/watch?v=nnktgWtfJHE&t=915s) So a few questions, honestly, that this brings up for me personally is that, is it just going to be tools talking to each other now, right? Are, are people just going to interface with the LLM and don't, don't have to even worry about learning the complex UI beneath it?

[15:32](https://www.youtube.com/watch?v=nnktgWtfJHE&t=932s) Because that's what seems to be happening, right? It's a whole new group of people that can come in and create now, and they can do it without learning the UI behind it.

[15:42](https://www.youtube.com/watch?v=nnktgWtfJHE&t=942s) And are creatives going to be more like orchestra conductors? Because, because now I think rather than knowing how to play the instrument, it's more important how to get the vision in your head and place it to the LLM so the LLM can execute it for you, and how you're conducting these different pieces that go together.

[16:01](https://www.youtube.com/watch?v=nnktgWtfJHE&t=961s) So it's an interesting time, I think, to be a creator, and MCPs are pretty much right at the center of it. And I think some of these examples like Blender MCP and Ableton MCP are examples of that.

[16:14](https://www.youtube.com/watch?v=nnktgWtfJHE&t=974s) And from that, there have been spurred a lot of MCPs for other creative tools, like I've seen for PostGIS, Houdini, Unity, Unreal Engine. There have been so many. So it's only a matter of time, I feel that, you know, this-- everyone can become a creator, uh, which is pretty cool.

[16:31](https://www.youtube.com/watch?v=nnktgWtfJHE&t=991s) Uh, thank you. Yeah, that's me. And, uh, yeah, you can find me on GitHub [REDACTED:username], and you can find me at Twitter [REDACTED:username]. Um, yeah. So thank you. Thank you for coming to this.

[16:44](https://www.youtube.com/watch?v=nnktgWtfJHE&t=1004s) And if you have any thoughts, please leave them in the comments. Thank you.
