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

  • 普通 tool 调用保持短切片,不等待整条 job 结束
  • 对外主流程暴露 6 个 job tools:
    • gauss_start_image_job
    • gauss_wait_current_stage
    • gauss_poll_job
    • gauss_get_job
    • gauss_resume_job
    • gauss_list_jobs
  • gauss_wait_current_stage 是默认等待手段:服务端内部执行 poll + wait,只等待“当前阶段结束”或一个 timeout_sec 切片,默认 60 秒;超时返回 status=in_progress
  • gauss_poll_job 保留给 debug 或细粒度观察,不再要求 agent 自己 Bash sleep
  • 通过阶段事件与阶段摘要给 skill 提供进度展示依据,而不是 fake percent
  • 紧凑 job 返回会在已有可展示全景图时携带 pano_url,供 skill 直接展示图片反馈
  • Claude Code skill 在启动新任务前会先确认是否清家具,并提示用户输入层高
  • 长耗时阶段按 15-30 秒节奏推进;同步 wait tool 会复用阶段轮询间隔,减少 transcript 噪音
  • 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

默认使用同步 wait tool:

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 \
  --wait-timeout-sec 60

如需切回细粒度 poll 调试:

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

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:

  • 启动新任务前会先询问是否清家具与层高,再显式调用 gauss_start_image_job
  • 主路径优先使用 gauss_wait_current_stage,不再要求 agent 自己 Bash sleep
  • 长耗时阶段默认按 60 秒切片同步等待,减少 transcript 噪音
  • job.pano_url 首次可用时,会在对话里展示全景图反馈
  • 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
  • gauss_poll_job 只保留给 debug 或细粒度观察

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-0.1.4.tar.gz (17.9 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-0.1.4-py3-none-any.whl (25.7 kB view details)

Uploaded Python 3

File details

Details for the file image_to_design_mcp-0.1.4.tar.gz.

File metadata

  • Download URL: image_to_design_mcp-0.1.4.tar.gz
  • Upload date:
  • Size: 17.9 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-0.1.4.tar.gz
Algorithm Hash digest
SHA256 6dca85e72dbdc6f2a117d507beafb4f538743bd9ae0a9d52204d94c62a13ef23
MD5 442fc04c29b13c7ccff73056efdc2b4c
BLAKE2b-256 89bbdf303b9ccf43bd7185a97c0fadc57acfbb498a7889eb08b921ca1b50a9d2

See more details on using hashes here.

File details

Details for the file image_to_design_mcp-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for image_to_design_mcp-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 4c9b5437add385b295944bf0302828998e3edf711a8a9e7dfa5549a37e533bd8
MD5 f37e87a0710b7ae587b4feec8df559c0
BLAKE2b-256 b8f59fb7efc83760915f0210b1ccc60d29802fe0d7e76e36f1af65d59b4b1d30

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