Connects to a running Blender desktop application through a local TCP bridge to provide tools for scene inspection, rendering multiple views, asset export, visual comparison, checkpoints, and controlled mesh operations.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
A Python MCP server that connects an AI client to a running Blender desktop application through a local TCP bridge. It exposes reusable tools for scene inspection, rendering, asset export, visual comparison, and controlled mesh operations.
Separate server, connection, visual-review, and sculpting modules.
Validate inputs and sanitize export paths before forwarding commands.
Provide project checkpoints and explicit operation limits.
Include portable setup, connection diagnostics, and troubleshooting documentation.
Cover non-Blender logic with automated tests, without requiring a running Blender instance.
Related MCP server: dcc-mcp-blender
MCP client -> Python MCP server (stdio) -> local TCP bridge -> Blender add-on
| |
input validation Blender main threadRequires Python 3.10+, uv, Blender, and an MCP-compatible client. The bundled launcher and setup helpers target macOS and Claude Code; other environments require manual client and Blender configuration.
uv sync
./bin/blender-mcp-setup.py --dry-run
./bin/blender-mcp-setup.py
./bin/blender-resolve.sh --gui
./bin/blender-mcp-health.pyReview setup output before enabling the integration. The setup helper writes project-local configuration; it does not modify global client settings. See usage and troubleshooting.
uv sync
PYTHONPATH=src uv run python -m unittest discover -s tests -vValidation on November 4, 2026: 299 tests passed with the development environment. These tests cover non-Blender logic and do not establish end-to-end Blender compatibility on every machine.
Example workflow: inspect the current scene, save a checkpoint, render multiple views, compare a render with a local reference, then export an asset. The detailed smoke-test recipe requires a running Blender instance.
This is a local desktop integration, not a hosted web API. The add-on can execute Python inside Blender and should be used only with trusted clients and commands. Keep the socket bound to localhost; do not expose it to untrusted networks. Retrying a command after a broken connection can repeat an operation. Save checkpoints before modifying important scenes.
Adapted from the MIT-licensed ahujasid/blender-mcp foundation. This version adds the validation, review, sculpting, setup, and testing layers described above. See NOTICE.md and LICENSE.
Connect your AI assistant to Blender for 3D modeling, Geometry Nodes, materials, lighting, animation, rendering and export. Inspect real scenes and viewport images, refine the result and restore checkpoints. OAuth connects your chat to Blender Bridge Desktop on an online Windows 10/11 x64 computer running Blender 4.2+. The chat can run on another device. Requires an active Blender Bridge account; 7-day trial available. AI model access is separate.
Blender-as-a-service for agents: search 3D assets, run Blender Python, or brief the studio agent.
Cloud Blender for AI agents: build, inspect, render and animate 3D scenes over remote MCP. Keep editable .blend projects and export GLB or STL. Make your first 3D asset free—30 compute minutes per UTC month, no credit card. First 100 eligible Free account owners to use all 30 minutes in one UTC month by December 31, 2026 UTC receive one calendar month of beta free: 4 compute hours per UTC month, 2 concurrent workers per deployment, 2 deployments, 2048×2048 renders at up to 256 samples, and 10 GiB storage. Existing usage counts toward the 4-hour allowance. Limited to 100 rewards; expires January 1, 2027 00:00 UTC. Free resumes afterward without an automatic charge. Examples, eligibility and terms: https://sceneplane.online/launch?utm_source=glama&utm_medium=directory&utm_campaign=first100
Blender and GLB/FBX/USD/STL rendered on cloud GPUs for AI agents: product shots, turntables, MP4
