Commerce-MCP
Enables natural-language control of e-commerce operations including product management, order processing, inventory tracking, customer service, content generation, and advertising analytics through 15 integrated MCP tools. Provides a local-first commerce automation solution with SQLite storage and extensible channel adapters for end-to-end online store workflows.
README
Commerce-MCP
자연어로 커머스 운영을 지시하면 상품, 주문, 재고, CS, 콘텐츠, 광고, 브리핑까지 로컬에서 이어서 처리하는 AI 기반 Commerce MCP 서버다.
Commerce-MCP is a local-first AI commerce MCP server that turns natural-language instructions into product, order, inventory, CS, content, ad, and daily-briefing workflows.
Structure
입력부터 운영 브리핑까지 흐름을 로컬 수직 슬라이스로 묶었다.
The current implementation is a local-first vertical slice that stretches from product input to daily operations.
Seller Prompt
-> commerce_parse_product
-> StandardProduct
-> Commerce Tools
-> ChannelTransformer / Builtin Logic
-> Mock Channel Adapters
-> SQLite
What It Does
현재 저장소는 아래 15개 MCP 도구를 로컬 내장형으로 제공한다.
This repository currently exposes the following 15 MCP tools in a local-first builtin form.
| ID | Tool | Role |
|---|---|---|
| 1 | commerce_parse_product |
자연어/JSON-like 상품 입력 파싱 |
| 2 | commerce_register_product |
채널별 상품 등록 mock |
| 3 | commerce_sync_product |
가격/재고/상품 상태 동기화 |
| 4 | commerce_collect_orders |
주문 수집 및 정규화 |
| 5 | commerce_process_orders |
송장 반영 및 출고 처리 |
| 6 | commerce_manage_inventory |
재고 경고 및 발주 추천 |
| 7 | commerce_generate_po |
발주서용 CSV/Markdown 생성 |
| 8 | commerce_collect_cs |
CS 수집 및 자동 분류 |
| 9 | commerce_respond_cs |
CS 답변 초안 생성 |
| 10 | commerce_generate_listing |
상품 상세 HTML 생성 |
| 11 | commerce_generate_image |
SVG 기반 상품 비주얼 생성 |
| 12 | commerce_create_ad |
광고 소재/캠페인 초안 생성 |
| 13 | commerce_report_ad |
광고 성과 리포트 |
| 14 | commerce_analytics |
주문/채널/매출 분석 |
| 15 | commerce_daily_briefing |
일일 운영 브리핑 생성 |
Current Mode
현재 구현 범위는 아래와 같다.
The current implementation includes the following:
| Area | Status |
|---|---|
| Product | 파싱, 등록, 동기화 지원 / parse, register, sync |
| Orders | 수집, 출고 처리, 일매출 집계 / collect, process, aggregate daily sales |
| Inventory | 저재고 경고, 발주서 생성 / low-stock alerts and purchase-order generation |
| CS | 문의 분류와 답변 초안 생성 / inquiry classification and draft response |
| Content | HTML 상세페이지와 SVG 비주얼 생성 / HTML listing and SVG visual generation |
| Ads & Analytics | 광고 초안, 광고 리포트, 분석, 브리핑 / ad draft, ad report, analytics, briefing |
| MCP Server | FastMCP 기반 15개 도구 노출 / FastMCP exposure for all 15 tools |
| Tests | 핵심 운영 흐름 검증 / coverage for core operating flows |
Quick Start
로컬에서 바로 실행하려면 아래 순서로 진행하면 된다.
Use the following steps to run the project locally.
python -m pip install -e .[dev]
pytest -q
python server.py
환경변수는 선택 사항이며 지정하지 않으면 프로젝트 루트의 commerce.db를 사용한다.
Environment variables are optional. If unset, the server uses commerce.db in the project root.
COMMERCE_MCP_DB_PATH=./commerce.db
Example Flow
보스가 실제로 쓰게 될 기본 흐름은 아래와 같다.
Here is the core operating flow the boss would actually use.
commerce_parse_product로 상품 입력 정규화commerce_register_product로 채널 mock 등록commerce_collect_orders로 주문 적재commerce_process_orders로 송장 반영 및 재고 차감commerce_manage_inventory와commerce_generate_po로 부족 재고 점검commerce_collect_cs와commerce_respond_cs로 문의 대응commerce_create_ad,commerce_report_ad,commerce_analytics,commerce_daily_briefing으로 운영 요약
Key Files
처음 들어왔을 때 보면 좋은 파일들이다.
These are the most useful entry points when you first open the project.
| Path | Purpose |
|---|---|
server.py |
실행 진입점 / runtime entrypoint |
core/server.py |
FastMCP app과 도구 등록 / FastMCP app and tool registration |
tools/product_parse.py |
상품 입력 파서 / product input parser |
tools/product_register.py |
등록 흐름과 DB 저장 / registration flow and persistence |
tools/order_collect.py |
주문 수집 / order collection |
tools/order_process.py |
주문 처리와 재고 반영 / order processing and inventory update |
tools/daily_briefing.py |
운영 브리핑 생성 / operations briefing |
core/db.py |
SQLite bootstrap과 저장소 / SQLite bootstrap and repository |
tests/ |
Phase 0 검증 세트 / Phase 0 verification suite |
Notes
현재 채널 연동은 mock/builtin 중심이다. 실제 쿠팡/네이버/11번가 API를 붙일 때는 ModuleAdapter와 채널 어댑터를 교체하면 된다.
Current channel integrations are mock-first. When real Coupang, Naver, or 11st APIs are ready, replace the builtin adapter path behind ModuleAdapter.
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.