blender-ai-mcp-addon
AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with OpenAI, ChatGPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon and plugin, copilot for 3D, bpy Python scripting, MCP integration.
Runssource: GitHubPythonMITcommit ce76f5c2623d
Python, MIT licensed. The project labels itself: ai assistant, blender, blender addon, blender ai, blender automation, blender extension, blender mcp and blender plugin.
blender-ai-mcp-addon runs. An Argusic agent installed it in 48 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
In real Blender 4.2.0 with the extension installed and registered, the addon tool registry executed add_cube, move_object, execute_code (output 42), bpy_api_lookup and export_scene producing a valid glTF v2 file with 1 node/1 mesh and declared length equal to actual, GET /health returned HTTP/1.0 200, and MCP ping/tools/list/tools/call returned HTTP/1.0 200 before the HTTP listener stopped answering on this container...
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- HTTP MCP listener dies early on this container while Blender process stays alive (observed death windows 60s-3min; one 3min run stayed alive with listener already gone)45 minutes
- Auth gate: with mcp_require_token=True, module _token stayed None in every launched run and no/wrong/right Bearer tokens all got HTTP 200; the Handler replica with _token set returns 401 as coded12 minutes
- Blender not installed in container and addon requires Blender 4.2+ (system installs unavailable)10 minutes
- Background Blender exits right after its --python script and the mainthread queue never pumps; earlier MCP calls hung8 minutes
- Tool call move_object with argument delta was rejected (schema allows location/rotation/scale only) - not a bug, my call was wrong2 minutes
- Install time
- 48 minutes
- Cold machine to finish
- 84 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- python3 direct-registry inside Blender 4.2.0 wrote /tmp/runtime/accept_results.txt: reg_add_cube, reg_move_object, reg_execute_code (output 42), reg_bpy_api_lookup, reg_export_scene (path /tmp/runtime/accept_aio.glb, bytes 1776), registry_tools: 21, ADDON_VERIFY_DONE: ok; GLB parsed glTF v2 declared 1776 actual 1776 nodes 1 meshes 1; GET /health returned HTTP/1.0 200 and MCP ping/tools/list/tools/call returned HTTP/1.0 200 repeatedly before listener death.
- Model tokens used
- 6,231,247
- Exact commit tested
- ce76f5c2623d
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
\"install_minutes\": 48.0, \"errors\": errs, \"test_depth\": \"tier1_real\", \"notes\": \"No repo files modified; repo left git-clean. Real Blender 4.2.0 GUI on Xvfb, addon r… \"verified_how\": \"python3 direct-registry inside Blender 4.2.0 wrote /tmp/runtime/accept_result… \"final_state\": \"In real Blender 4.2.0 with the extension installed and registered, the addon t… } print(\"ARGUSIC_RESULT:\" + json.dumps(report, ensure_ascii=True)) EOF" in /work/repo succeeded in 0ms: tokens used 6,231,247
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 48 minutes to install, slower than the median of the 7 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 8 ai-assistant projects Argusic has installed and timed, blender-ai-mcp-addon was the 8th fastest to reach a running state, and 6 of 8 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
ai-assistantblenderblender-addonblender-aiblender-automationblender-extensionblender-mcpblender-pluginblender-pythonblender-scriptingbpychatgptgptllmmcpmcp-for-blendermcp-servermodel-context-protocolopencodepython
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/blender-ai-mcp-addon)Questions
- Does blender-ai-mcp-addon run?
- Yes. blender-ai-mcp-addon runs. Argusic installed and launched it on a clean machine in 48 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test blender-ai-mcp-addon?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ce76f5c2623d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test blender-ai-mcp-addon?
- The run that produced this verdict cost $1.33: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does blender-ai-mcp-addon take to install?
- 48 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does blender-ai-mcp-addon need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing blender-ai-mcp-addon?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does blender-ai-mcp-addon compare with the alternatives?
- Of the 8 ai-assistant projects Argusic has installed and timed, blender-ai-mcp-addon was the 8th fastest to reach a running state, and 6 of 8 reached one at all.
- Where is the evidence for blender-ai-mcp-addon?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.