PointCloud MCP

PointCloud MCP

Enables querying 3D point cloud files (PLY/PCD) using natural language. Provides tools for point cloud description, plane detection, and ICP alignment.

Category
Visit Server

README

PointCloud MCP

3D Point Cloud(.ply/.pcd)를 자연어로 질의하는 MCP 서버. "3D 데이터를 LLM이 다루게 한다"는 아이디어를 open3d로 구현한 포트폴리오 데모. 3D Computer Vision(MVSNet·ICP·Point Cloud) 경험과 LLM/MCP 툴링을 결합한 차별화 프로젝트.

실행 증거

아래 이미지는 2026-07-14에 클린 Python 3.12 가상환경에서 MCP stdio 연결 후 tools/listdescribe_pointcloud를 실제 호출한 결과입니다.

PointCloud MCP smoke test

검증 결과
pip install -e ".[dev]" 통과 (Python 3.12.11)
python -m pytest -q 1 passed
MCP initialize · tools/list 통과 — 3 tools
describe_pointcloud 호출 통과 — 합성 PLY 1,000 points

현재 Open3D macOS wheel 호환성을 기준으로 Python 3.10–3.12를 지원합니다.

왜 만들었나

3D 재구성·정렬을 실무에서 다뤄온 엔지니어가, 그 도메인을 LLM 도구 생태계(MCP)에 노출하면 어떤 일이 가능한지 보여주기 위한 데모입니다. LLM 클라이언트가 3D 파일의 기하 속성을 이해하고, 평면을 검출하고, 두 스캔을 정렬(ICP)하도록 합니다.

노출 도구 (MCP tools)

도구 설명
describe_pointcloud(path) 점 개수·bounding box·centroid 등 요약
detect_plane(path) RANSAC으로 지배적 평면(바닥/벽) 검출
align(path_a, path_b) 두 Point Cloud를 ICP로 정렬, fitness/RMSE 반환

빠른 시작

python3.12 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"             # open3d, numpy, mcp, pytest

# 샘플 Point Cloud 생성 (바닥 평면 + 벽, ICP용 이동본)
python data/make_sample.py

# MCP 없이 바로 테스트
python -m src.cli describe data/scan_a.ply
python -m src.cli plane    data/scan_a.ply
python -m src.cli align    data/scan_a.ply data/scan_b.ply

# 단위 테스트
python -m pytest -q

MCP 클라이언트 연결 (Claude Desktop)

{
  "mcpServers": {
    "pointcloud": {
      "command": "python",
      "args": ["/absolute/path/to/pointcloud-mcp/server.py"]
    }
  }
}

예: "scan_a.ply의 점이 몇 개고 바닥 평면은 어디야?"describe_pointcloud + detect_plane 호출

기술 스택

Python · open3d · NumPy · MCP

데이터

data/make_sample.py가 생성하는 합성 Point Cloud. 외부/회사 데이터 없음. 실제 데이터로 쓰려면 Stanford Bunny, ScanNet 샘플 등 공개 데이터셋을 넣으면 됩니다.

관련 글

라이선스

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured