DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run a manager, worker and reviewer team on a scene task with Blender AI MCP Addon

Split a larger Blender task across a manager, workers and reviewers with ordered steps.

  • Content
  • Advanced
  • 60 minutes
  • From the README
  • Any agent

Authorization notice. Blender AI MCP Addon is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA technical artist who wants larger scene changes checked before they are accepted.

The problemA single assistant can make many edits in one pass, which is hard to verify and easy to lose track of.

The outcomeA sequential run where assignments, attempts and review findings appear on the task board, and approved work is kept.

What you need first

  • Blender 4.2 or later; the release bundle targets Windows x64
  • The mcp-for-blender-pro.zip file from the GitHub Releases page
  • An account and API key for a supported provider (OpenAI, Anthropic Claude, Google Gemini, OpenRouter, OpenCode Zen), or a local Ollama install, or a compatible custom endpoint
  • Service keys for Poly Haven, Sketchfab or Poly Pizza if you want asset search and import

Steps

  1. Install and enable mcp-for-blender-pro in Blender.
  2. In the Studio window, switch from Single assistant to a Team chain.
  3. Assign a manager, one or more workers and reviewers, each with instructions and a model.
  4. Send the task, then watch the task board for assignments, attempts and review findings.
  5. Accept the approved result, or review the findings if a second review fails and the workflow stops.

Prompt for your agent

Using the mcp-for-blender-pro team chain in Blender, run a manager, worker and reviewer workflow to <describe the scene change>. Expect a final summary listing each assignment, its attempt count and the reviewer's approval or findings. Verify that the task board shows tasks completed in order and that no task was left in a blocked state.

Caveat. Each team member can use a different model, which raises cost and makes results harder to reproduce, so keep the team small at first.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page