User MCP Demo
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@User MCP DemoRegister a new user with username alice and email alice@example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
User MCP Demo
学习项目:先提供用户与账单 REST API,再基于这些接口构建 Streamable HTTP MCP Server,覆盖 MCP 三要素(Tools / Resources / Prompts)。
生产环境里
app与mcp_server完全可以拆成两个仓库:MCP 只通过 HTTP 调用已有微服务,旧服务无需改动。
架构
┌──────────────────────┐ HTTP /mcp ┌──────────────────────┐
│ MCP Client │ ──────────────────────────▶ │ MCP Server :3001 │
│ (Cursor / scripts) │ │ Streamable HTTP │
└──────────────────────┘ │ tools/resources/ │
│ prompts │
└──────────┬───────────┘
│ httpx
▼
┌──────────────────────┐
│ User REST API :8000 │
│ FastAPI + SQLite │
└──────────────────────┘Related MCP server: Basic MCP Server
快速开始
cd /Users/jasqia/00D_PythonProject/my-mcp
source .venv/bin/activate
pip install -r requirements.txt
# 终端 1:启动 REST API
uvicorn app.main:app --host 127.0.0.1 --port 8000 --reload
# 终端 2:启动 MCP Server(Streamable HTTP)
python -m mcp_server
# 等价:python -m mcp_server.serverREST 文档:http://127.0.0.1:8000/docs
MCP 端点:http://127.0.0.1:3001/mcp
REST API
用户
方法 | 路径 | 说明 |
POST |
| 注册 |
POST |
| 登录,返回 JWT |
GET |
| 当前用户(需 Bearer Token) |
PATCH |
| 更新个人信息(需 Bearer Token) |
账单
方法 | 路径 | 说明 |
POST |
| 创建自己的账单 |
GET |
| 读取自己的账单列表 |
GET |
| 别人分享给自己的账单 |
GET |
| 读取单条(自己的或分享给自己的) |
PATCH |
| 更新自己的账单 |
DELETE |
| 删除自己的账单 |
POST |
| 分享给其他用户阅读 |
DELETE |
| 取消分享 |
POST |
| 点赞(自己的或已分享给自己的) |
DELETE |
| 取消点赞 |
示例
# 登录拿 TOKEN 后创建账单
curl -s http://127.0.0.1:8000/api/bills \
-H "Authorization: Bearer TOKEN" \
-H 'Content-Type: application/json' \
-d '{"title":"午餐","amount":"32.50","category":"food","spent_at":"2026-08-11"}'
# 分享给 bob
curl -s http://127.0.0.1:8000/api/bills/1/share \
-H "Authorization: Bearer TOKEN" \
-H 'Content-Type: application/json' \
-d '{"username":"bob"}'
# 点赞
curl -s http://127.0.0.1:8000/api/bills/1/like \
-X POST \
-H "Authorization: Bearer TOKEN"MCP 三要素
Tools
用户
register_user/login_user/get_current_user/update_user_profile
账单
create_bill/list_my_bills/list_shared_bills/get_billupdate_bill/delete_billshare_bill/unshare_billlike_bill/unlike_bill
Resources
user://api/health— API 健康检查user://docs/overview— 项目说明user://profile/{access_token}— 当前用户资料bill://mine/{access_token}— 我的账单列表bill://shared/{access_token}— 分享给我的账单bill://item/{access_token}/{bill_id}— 单条账单
Prompts
welcome_new_user— 欢迎新用户help_update_profile— 协助更新资料help_create_bill— 协助记账help_share_bill— 协助分享账单help_like_bill— 协助点赞
Cursor 连接(Streamable HTTP)
{
"mcpServers": {
"user-mcp": {
"url": "http://127.0.0.1:3001/mcp"
}
}
}本地验证
source .venv/bin/activate
pip install -r requirements-dev.txt # 首次需要
# 推荐:一条命令跑 pytest(无需先起服务)
make test
# 或:
# make test-api
# make test-mcp
# make test-e2e # 只跑 L4 Streamable HTTP 等 e2e 标记
# 测试分层说明(L2 Mock / L4 真传输等):docs/MCP_L2_L4_EXPLAINED.zh.md
# 手工 E2E 冒烟(需先启动 API;MCP 脚本还需启动 MCP)
python scripts/test_user_client.py
python scripts/test_bill_client.py
python scripts/test_mcp_user_client.py
python scripts/test_mcp_bill_client.py目录结构
my-mcp/
├── app/ # FastAPI REST API
│ ├── __init__.py
│ ├── main.py # 应用入口
│ ├── config.py # 配置(端口、数据库、JWT)
│ ├── database.py # SQLAlchemy / SQLite
│ ├── models.py # User / Bill / BillShare / BillLike
│ ├── schemas.py # 请求/响应 Pydantic 模型
│ ├── auth.py # 密码哈希、JWT、鉴权依赖
│ ├── services.py # 用户业务逻辑
│ ├── bill_services.py # 账单业务逻辑
│ └── routers/
│ ├── __init__.py
│ ├── users.py # /api/users
│ └── bills.py # /api/bills
├── mcp_server/ # Streamable HTTP MCP Server
│ ├── __init__.py
│ ├── __main__.py # python -m mcp_server
│ └── server.py # Tools / Resources / Prompts
├── tests/ # pytest 套件
│ ├── conftest.py
│ ├── api/
│ │ ├── test_users.py
│ │ └── test_bills.py
│ └── mcp/
│ ├── surface.golden.json # L1b 表面指纹
│ ├── test_tool_contract.py
│ ├── test_surface_drift.py
│ ├── test_protocol_behavior.py
│ ├── test_resources_prompts.py
│ ├── test_tool_http_wiring.py # L2 Mock:tool→REST 接线
│ └── test_streamable_http_transport.py # L4:真 Streamable HTTP /mcp
├── scripts/
│ ├── http_helpers.py # REST 测试公共工具
│ ├── mcp_helpers.py # MCP 测试公共工具
│ ├── test_user_client.py # 手工 E2E:用户 REST
│ ├── test_bill_client.py # 手工 E2E:账单 REST
│ ├── test_mcp_user_client.py # 手工 E2E:MCP 用户
│ └── test_mcp_bill_client.py # 手工 E2E:MCP 账单
├── data/
│ └── users.db # SQLite 数据库(运行后生成)
├── Makefile
├── pytest.ini
├── requirements.txt
├── requirements-dev.txt
├── TESTING_IMPROVEMENT_PLAN.zh.md
└── README.mdThis 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-qualityDmaintenanceA demonstration server showing MCP implementation in Python with resource handling, tool operations, and reusable prompts for a simple user/post system with local database.
- Alicense-qualityDmaintenanceA minimal demonstration server showcasing MCP protocol capabilities including tools, resources, and prompts with basic examples like hello world functionality.3MIT
- Flicense-qualityDmaintenanceEducational example of an MCP server built with FastMCP, demonstrating how to expose tools, resources, and prompts for AI clients.
- Flicense-qualityCmaintenanceDemonstrates how to create a simple MCP server with streamable HTTP transport, featuring tools, prompts, and resources.4
Related MCP Connectors
MCP server exposing the Backtest360 engine API as tools for AI agents.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
MCP server for Argo RPG Platform — connects AI assistants to campaign data via OAuth2
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/bot-qianjinyan/my-mcp-user'
If you have feedback or need assistance with the MCP directory API, please join our Discord server