Skip to main content

MCP server for image-to-design workflow automation

Project description

gauss-mcp

基于 uv 管理的 Python MCP server,用于把本地图片导入为方案,并通过 job 协议提供可轮询的进度与结果。

当前 MVP 范围

  • 输入本地图片路径
  • 上传图片
  • 判断普通图/全景图
  • 普通图转全景图
  • 可选清家具
  • 全景图转点云
  • 空间调整
  • 导入方案
  • 返回 design link

核心设计

  • 单次 tool 调用只做有限工作,不阻塞等待整条链路结束
  • 对外主流程只暴露 5 个 job tools:
    • gauss_start_image_job
    • gauss_poll_job
    • gauss_get_job
    • gauss_resume_job
    • gauss_list_jobs
  • 通过阶段事件而不是 fake percent 给 skill 提供进度展示依据
  • 长耗时阶段按低频轮询推进,默认 15-30 秒一轮,避免大量碎片化等待输出
  • gauss_import 完成后会立即产出 design_url,用户可以先打开方案预览;gauss_show_info 继续补齐 splat_url / drc_url
  • job 状态落盘到 IMAGE_TO_DESIGN_JOB_STATE_DIR,支持中断后继续查询或恢复

阶段顺序

  1. upload
  2. image_type
  3. img2pano
  4. pano_clear
  5. pano2pointcloud
  6. spatial_tune
  7. gauss_import
  8. gauss_show_info

开发

uv sync --dev
uv run pytest
uv run ruff check src tests

运行 MCP Server

uv run gauss-mcp

本地 smoke test

uv run python scripts/e2e_image_to_plan.py /absolute/path/to/image.png

可选参数:

uv run python scripts/e2e_image_to_plan.py /absolute/path/to/image.png \
  --floor-plan-name demo-plan \
  --level-height-mm 2800 \
  --no-clear-furniture

Claude Code Skill

Skill 位于:

.claude/skills/gauss-image-to-plan/SKILL.md

它基于 gauss_* job tools 做阶段式编排:

  • 长耗时阶段默认按约 30 秒节奏低频心跳
  • gauss_import 完成后先返回可预览的 design_url
  • gauss_show_info 继续补齐 splat_url / drc_url

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

image_to_design_mcp-0.1.1.tar.gz (16.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

image_to_design_mcp-0.1.1-py3-none-any.whl (24.3 kB view details)

Uploaded Python 3

File details

Details for the file image_to_design_mcp-0.1.1.tar.gz.

File metadata

  • Download URL: image_to_design_mcp-0.1.1.tar.gz
  • Upload date:
  • Size: 16.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for image_to_design_mcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 cf7efbc2a51d8771c0a4dbfff39a1f48ed7b62e074291b80f3a750619777cf35
MD5 927945f291d9d27e4e7b34b2a21814a9
BLAKE2b-256 83a484d651afb75be4c274a386725f83d00ebd31dc7c7c44ff99358c1c39f344

See more details on using hashes here.

File details

Details for the file image_to_design_mcp-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for image_to_design_mcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 c179347e906a4264f921fe9dae8104498f55c6fad08a4637ceb8521cd0ebe235
MD5 e49d9fef8d0eadcedee4a23eb638ce88
BLAKE2b-256 828e593a18e99ff5b9faa2765306ea160710c9009ab5c91ab3ca7a4b92deae5e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page