{"id":30869137,"url":"https://github.com/FishWoWater/trellis_mcp","last_synced_at":"2025-09-07T22:16:15.215Z","repository":{"id":286417339,"uuid":"954780170","full_name":"FishWoWater/trellis_mcp","owner":"FishWoWater","description":"Model Context Protocol(MCP) for TRELLIS(SOTA text-to-3d/image-to-3d) models","archived":false,"fork":false,"pushed_at":"2025-04-06T10:13:32.000Z","size":2736,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-06T11:22:55.925Z","etag":null,"topics":["blender","image-to-3d","mcp","mcp-server","text-to-3d","trellis"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FishWoWater.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-25T15:51:52.000Z","updated_at":"2025-04-06T10:13:36.000Z","dependencies_parsed_at":"2025-04-06T11:33:04.791Z","dependency_job_id":null,"html_url":"https://github.com/FishWoWater/trellis_mcp","commit_stats":null,"previous_names":["fishwowater/trellis_mcp"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/FishWoWater/trellis_mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FishWoWater%2Ftrellis_mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FishWoWater%2Ftrellis_mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FishWoWater%2Ftrellis_mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FishWoWater%2Ftrellis_mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FishWoWater","download_url":"https://codeload.github.com/FishWoWater/trellis_mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FishWoWater%2Ftrellis_mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274102850,"owners_count":25222680,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-07T02:00:09.463Z","response_time":67,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["blender","image-to-3d","mcp","mcp-server","text-to-3d","trellis"],"created_at":"2025-09-07T22:04:01.805Z","updated_at":"2025-09-07T22:16:15.194Z","avatar_url":"https://github.com/FishWoWater.png","language":"Python","funding_links":[],"categories":["🤖 AI/ML"],"sub_categories":[],"readme":"# Trellis MCP Server\n\nTrellis MCP provides an interface between AI assistants and [Trellis](https://github.com/microsoft/TRELLIS) via [Model Context Protocol (MCP)](https://modelcontextprotocol.io). \n\n### Disclaimer\nThis project shows a very **minimal** integration of MCP with [Trellis](https://github.com/microsoft/TRELLIS): a lightweight and opensource text-to-3d/image-to-3d 3DAIGC model. Compared with existing [rodin integration in blender-mcp](https://github.com/ahujasid/blender-mcp) and [tripo integration](https://github.com/VAST-AI-Research/tripo-mcp), it has following advantages: \n* **Faster and memory-efficient**: You can deploy TRELLIS **locally with only 8GPU+ VRAM**, while can generate a textured mesh from text in only *~15s*(10s with more vram).\n* **FREE**: You DON'T have to pay expensive API from Rodin/Meshy/Tripo.\n\n**BUT IT HAS FOLLOWING LIMITATIONS:**\n* Trellis is open-source and there is no off-the-shelf API model providers, you have to deploy it by yourself (refer to [README](https://github.com/FishWoWater/TRELLIS/blob/dev/README_api.md)).\n* The API/Prompt has NOT been fully tested/tuned, may suffer from stability issues. \n\nSo use it at your own risk. \n\n## Demo \n\u003e A minimal demo for generating a single object, more complicated prompt with blender-mcp is under tuning.\n\n![Demo](assets/trellis_mcp_demo2.gif)\n\n## Features\n\n- [x] Generate 3D asset from natural language(**TEXT**) using Trellis API and import into blender\n- [ ] Generate texture/materials from natural language(**TEXT**) for a given 3D mesh using Trellis API and import into blender\n\n## Roadmap  \n\n### Prerequisites\n- Python 3.10+\n- [Blender](https://www.blender.org/download/)\n- [Trellis Blender Addon](https://github.com/FishWoWater/trellis_blender)\n- [Trellis API Backend](https://github.com/FishWoWater/TRELLIS)\n- Claude / Cursor(SUGGESTED) / Windsurf\n\n### Installation\n#### 1. Trellis blender addon \n1. Download Trellis Blender Addon from [here](https://github.com/FishWoWater/trellis_blender)\n2. Open Blender -\u003e Edit -\u003e Preferences -\u003e Add-ons -\u003e Install from file -\u003e Select the downloaded addon -\u003e Install\n3. In 3D Viewport -\u003e View3D \u003e Sidebar \u003e TRELLIS -\u003e Start MCP Server \n\n#### 2. Configure API backend \n\u003e As trellis is a free open-source text-to-3d model, you need to deploy your own trellis API backend with reference to [README](https://github.com/FishWoWater/TRELLIS/blob/dev/README_api.md)\n``` shell \n# clone an API fork of trellis \ngit clone https://github.com/FishWoWater/TRELLIS\ncd TRELLIS\n\n# EDIT BACKEND URL in trellis_api/config.py\n\n# configure the # of text workers and start ai worker\n# no need for image workers \npython trellis_api/ai_worker.py --text-workers-per-gpu 1 --image-workers-per-gpu 0\n\n# start web server \npython trellis_api/web_server.py \n\n# or on windows local dev \npython trellis_api/web_server_single.py \n```\n\n#### 3. Configure the MCP server on Windsurf/Cursor/Claude \n```text \n{\n    \"mcpServers\": {\n        \"trellis-blender\": {\n            \"command\": \"uvx\",\n            \"args\": [\n                \"trellis-mcp\"\n            ]\n        }\n    }\n}\n```\n\n## Acknowledgements\n- Backbone and brain: [Trellis](https://github.com/microsoft/TRELLIS)\n- Inspiration: [blender-mcp](https://github.com/ahujasid/blender-mcp)\n- Borrow a lot of code [Tripo MCP Service](https://github.com/VAST-AI-Research/tripo-mcp)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFishWoWater%2Ftrellis_mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FFishWoWater%2Ftrellis_mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFishWoWater%2Ftrellis_mcp/lists"}