Commerce Ai Agent
БесплатноНе проверенMulti-agent AI system for e-commerce automation — inventory, pricing, customer service, and marketing agents powered by MCP (Model Context Protocol). Built with
Описание
Multi-agent AI system for e-commerce automation — inventory, pricing, customer service, and marketing agents powered by MCP (Model Context Protocol). Built with FastAPI + React.
README
CommerceAI Agent is an experimental e-commerce automation application with a FastAPI backend, React dashboard, asynchronous task definitions, integration models, and MCP-oriented agent adapters.
The repository demonstrates architecture and interface concepts. Several screens use sample data, and external services require separate credentials, servers, and validation before they can operate.
Feature status
| Feature | Implemented | Mocked | Planned | Evidence |
|---|---|---|---|---|
| FastAPI application and domain routes | Yes | No | No | src/main.py, src/api/ |
| User, store, product, order, customer, and integration models | Yes | No | No | src/models/, src/schemas/ |
| React administration interface | Yes | Partly | No | frontend/src/; several pages include sample fallback data |
| PostgreSQL, Redis, RabbitMQ, and Celery topology | Partly | No | No | Docker Compose and task definitions exist; end-to-end operation is not demonstrated by integration tests |
| JWT-oriented authentication flow | Partly | No | No | Auth routes and helpers exist; production hardening is not established |
| MCP client and agent adapters | Partly | No | No | Client wrappers exist and require an external MCP server |
| Inventory, pricing, marketing, customer-service, and email agents | Partly | Partly | No | Adapter classes exist; behavior depends on external MCP functions or LLM services |
| WooCommerce client | Yes | No | No | src/integrations/woocommerce/client.py |
| Shopify client | Yes | No | No | src/integrations/shopify/client.py |
| Stripe and PayPal client wrappers | Yes | No | No | src/integrations/payment/ |
| Amazon and eBay marketplace integration | No | Interface only | Yes | Providers appear in UI/configuration lists; no corresponding client implementation is present |
| HubSpot and Salesforce integration | No | Interface only | Yes | Listed as providers without client implementations |
| DHL, UPS, and FedEx integration | No | Interface only | Yes | Listed as providers without client implementations |
| Autonomous production operation | No | No | Yes | No evidence of a validated autonomous production deployment |
| Mobile application | No | No | Yes | Roadmap only |
| ERP integrations | No | No | Yes | Roadmap only |
Implemented project surface
- FastAPI route structure for common commerce entities
- SQLAlchemy models and Pydantic schemas
- React pages for products, orders, customers, stores, agents, and integrations
- Celery task modules for pricing, inventory, marketing, email, and customer service workflows
- MCP client abstractions for invoking separately hosted functions
- Client wrappers for selected marketplace and payment providers
- Docker Compose definitions for the application and supporting services
Important limitations
- The repository does not include an MCP server implementing the functions called by the agent adapters.
- UI sample data can be displayed when API queries are unavailable; it must not be interpreted as live store data.
- Listing a provider in the settings interface does not mean its external API is implemented or verified.
- External integrations require provider credentials and have not been certified here for production use.
- The repository does not contain a backend unit or integration test suite.
- No claim is made that the system can run unattended or safely modify a live commerce account.
Architecture
React dashboard
|
FastAPI routes
|
SQLAlchemy models ---- PostgreSQL
|
Celery tasks ---------- RabbitMQ / Redis
|
Agent adapters -------- external MCP server (not included)
|
Selected provider client wrappers
Local setup
Prerequisites
- Python 3.9+
- Node.js
- Docker and Docker Compose
Configuration
The application expects environment configuration, but no committed
.env.example is present. Review src/core/config.py and create a local .env
containing only the values required for the components you intend to evaluate.
Do not commit credentials.
Backend
python -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt
uvicorn src.main:app --reload
Frontend
cd frontend
npm install
npm start
Docker Compose
Docker Compose defines the API, frontend, PostgreSQL, Redis, RabbitMQ, Celery worker, and Flower services:
docker compose up --build
This path requires a valid local .env and should be treated as an
experimental development setup.
Technology
- Python, FastAPI, Pydantic, SQLAlchemy
- PostgreSQL, Redis, RabbitMQ, Celery
- React and Material UI
- HTTPX-based MCP client
- Docker Compose
Roadmap
- Complete and test external provider integrations
- Provide an in-repository MCP server or documented compatible implementation
- Replace UI fallback data with explicit demo fixtures
- Add backend unit and integration tests
- Validate background workflows end to end
- Add mobile, ERP, and additional marketplace support only after implementation
License
The repository is licensed under the MIT License.
Установка Commerce Ai Agent
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/vinsblack/commerce-ai-agentFAQ
Commerce Ai Agent MCP бесплатный?
Да, Commerce Ai Agent MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Commerce Ai Agent?
Нет, Commerce Ai Agent работает без API-ключей и переменных окружения.
Commerce Ai Agent — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить Commerce Ai Agent в Claude Desktop, Claude Code или Cursor?
Открой Commerce Ai Agent на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare Commerce Ai Agent with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
