semantic-product-search-mcp
语义化商品搜索
语义化商品搜索:不是匹配关键词,而是理解查询意图(嵌入 + 相似度搜索),并使用智能体生成针对商品目录的推荐。商品目录以 MCP 服务器形式暴露,由独立的智能体消费。
🚧 项目正在积极开发中。当前处于第一阶段 · 后端搭建。 架构、演示和设计决策部分将在后续端到端流程可用时补充。
技术栈
API: FastAPI
智能体 / 编排: LangChain + LangChain Anthropic (Claude)
本地模型: Ollama
可观测性: LangSmith
配置 / 验证: Pydantic + Pydantic Settings
数据库: Postgres + pgvector(本地开发:SQLite)
包管理器: uv
Related MCP server: Vertex AI Search for Commerce MCP Server
项目结构
app/
main.py # entrypoint de la API
api/routes.py # rutas HTTP
catalog/ # ingesta + modelos de datos del catálogo
search/ # embeddings + similarity search
reviews/
mcp_server/ # servidor MCP (expone el catálogo/búsqueda como tools)
agent/ # agente que consume el MCP y arma la recomendación
core/
config.py # settings (variables de entorno)
db.py # conexión a Postgres/pgvector
models/
schemas.py # modelos Pydantic compartidos
tests/本地搭建
要求:Python >= 3.12 并已安装 uv。
# Instalar dependencias
uv sync
# Configurar variables de entorno
cp .env.example .env
# completar ANTHROPIC_API_KEY y LANGSMITH_API_KEY en .env
# Correr el entrypoint
uv run python -m app.main环境变量
变量 | 默认值 | 描述 |
|
| 运行环境 |
|
| 启用 LangChain 在 LangSmith 中的追踪 |
|
| LangSmith 端点 |
| (必填) | LangSmith API 密钥 |
|
| LangSmith 中的项目名称 |
| (必填) | Anthropic (Claude) API 密钥 |
|
| 数据库连接字符串 |
|
| 嵌入模型 |
|
| 用于相似度搜索的模型 |
|
| 每次搜索返回的结果数量 |
⚠️ 切勿记录 API 密钥或任何机密信息的值(
ANTHROPIC_API_KEY、LANGSMITH_API_KEY等)。如果需要调试Settings,仅打印失败的字段名称,而非其值——app/core/config.py在启动时验证时正是这样做的。
路线图
开发按阶段组织(参见 Notion 看板):
后端搭建
商品目录 + 嵌入
语义搜索
评论 + 反馈
MCP 服务器
智能体 + 推荐
REST API + 流式传输
优化
前端 + 发布
架构与设计决策
待定——将在第九阶段(PROD-32)记录,届时项目具备端到端流程,可以基于实际上下文描述图表、演示和决策(缓存、检索 + 重排序等)。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityDmaintenanceEnables semantic search and natural language product recommendations using ChromaDB vector store and Azure OpenAI embeddings. Supports multi-filter search by category, brand, and price with 8 specialized MCP methods for intelligent product discovery.
- Flicense-qualityDmaintenanceProvides Vertex AI Search for Commerce product search as a tool, enabling AI agents to search product catalogs using natural language queries.
- AlicenseAqualityDmaintenanceKlarna-style product discovery for AI shopping agents. Makes product catalogs machine-readable so AI agents can search, compare, and purchase products programmatically.6MIT
- Flicense-qualityDmaintenanceEnables natural language product management (CRUD) with multiple classification methods, including LLM-based and fast ML classifiers, for product creation, listing, updating, and deletion via a chat interface.1
Related MCP Connectors
Agent-native product catalog for AI shopping agents. 296M+ products, 28 countries.
Product discovery for AI agents: ranked products and bundles from the open merchant web.
Policy review and purchase discovery for AI-agent commerce actions.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sebastian946/SemanticProductSearch'
If you have feedback or need assistance with the MCP directory API, please join our Discord server