Coffee Company MCP Server
An MCP adapter that maps Coffee Company B2B HTTP APIs to MCP tools, allowing AI agents to query member information, benefits, coupons, and payment statuses. It enables seamless integration for AI assistants to manage coffee-related customer assets and loyalty details through natural language.
README
Coffee Company MCP Server
Coffee Company B2B 开放平台 MCP Server —— 让 AI Agent 通过 MCP 协议调用Coffee Company现有 HTTP 开放平台能力。
所有 MCP Tool 严格 1:1 映射
openapi.coffeecompany.com现有 HTTP 接口,不新增业务逻辑。 鉴权由 Kong 网关处理,MCP 层只做协议转换 + 语义化格式化。
Quick Start
# 安装依赖 (需要 uv + Python 3.13)
uv sync
# 运行完整 Demo(9 步流程演示)
uv run coffee demo
# 交互式模式
uv run coffee interactive
Architecture
B2B Agent (蔚来/千问/飞猪)
│ MCP Protocol (SSE / Streamable HTTP)
▼
┌──────────── Kong ────────────┐
│ HMAC Auth ✓ ACL ✓ 限流 ✓ │ ← 复用现有 B2B 客户凭证
│ │
│ /sse, /mcp → MCP Adapter │ ← 新增 2 条路由
│ /coupon/* → 现有后端 │ ← 不动
└──────────────┬───────────────┘
▼
MCP Adapter (本项目)
├── MCP 协议处理
├── Tool 权限过滤
├── 参数映射
└── 语义化转换
│ 内网直连
▼
openapi-platform 后端 (不动)
Phase 1 Tools(10 个只读,当前可用)
| MCP Tool | HTTP API | 功能 |
|---|---|---|
member_query |
POST /crmadapter/account/query |
查询会员信息 |
member_tier |
POST /crmadapter/account/memberTier |
会员等级详情 |
member_benefits |
POST /crmadapter/customers/getBenefits |
8 项权益状态 |
member_benefit_list |
POST /crmadapter/asset/coupon/getBenefitList |
券列表 |
coupon_query |
POST /coupon/query |
订单券码查询 |
coupon_detail |
POST /coupon/detail |
券码详情 |
equity_query |
POST /equity/query |
权益发放查询 |
equity_detail |
POST /equity/detail |
权益详情 |
assets_list |
POST /assets/list |
客户全部资产 |
cashier_pay_query |
POST /cashier/payQuery |
支付状态查询 |
CLI 命令
uv run coffee member 138****1234 # 查会员(手机号)
uv run coffee member CC_M_100001 # 查会员(会员ID)
uv run coffee tier CC_M_100001 # 等级详情
uv run coffee benefits CC_M_100001 # 权益状态
uv run coffee assets CC_M_100001 # 全部资产
uv run coffee coupon CC20260301A001 # 券码详情
uv run coffee equity EQ_2026030100001 # 权益详情
uv run coffee pay PAY_TOKEN_001 # 支付状态
接入 Claude Code / Cursor
{
"mcpServers": {
"coffee-company": {
"command": "uv",
"args": ["--directory", "/path/to/coffee-company-mcp", "run", "coffee-company-mcp"]
}
}
}
B2B 场景示例
蔚来车机 Agent:
车主: "帮我查一下我的Coffee Company会员等级和可用优惠券"
Agent 调用链:
member_query(mobile="138****1234") → 确认金星会员
member_tier(member_id="CC_M_100001") → 142 颗星,距钻星差 358 颗
assets_list(member_id="CC_M_100001") → 3 张可用券
Docs
- Architecture — 完整 API 映射表 + 分期开放策略
- Deploy Decision — Kong 架构下的部署方案分析
License
MIT
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.