nemlig-mcp
Enables searching products, viewing product details, managing the basket, and accessing order history on nemlig.com through natural language. It does not support placing orders or accessing payment cards.
README
nemlig-mcp
Unofficial local MCP for nemlig.com, danish delivery service
Built as a thin layer over nemlig_cli,
which already solves the hard parts: the three-step XSRF/bearer/login flow, the
cookie-backed session, the two different API hosts, and the GetAsJson
endpoints. This package adds a token-refresh loop, a privacy filter, and a
curated tool surface.
Tools
| Tool | Writes? | Description |
|---|---|---|
search_products |
no | Search the catalogue |
get_product_details |
no | Nutrition, allergens, attributes |
get_basket |
no | Current basket contents |
add_to_basket |
yes | Add a product to the basket |
get_order_history |
no | Previous orders |
get_order_details |
no | Line items of one past order |
What this server deliberately cannot do
It cannot place an order or read your payment cards. Nemlig's API exposes
POST /webapi/Order/PlaceOrderLoggedIn (which charges a saved card) and
GET /webapi/Checkout/GetCreditCards. nemlig_cli implements neither, and this
server does not add them.
The tool surface is an allowlist, not a filtered view of the whole API, so an
endpoint cannot become reachable by accident. A test asserts this
(tests/test_server.py). add_to_basket is the only
tool that changes state, and filling a basket is reversible on the website.
Privacy
Basket and order responses embed the account holder's name, street address and
phone number. Everything a tool returns lands in the model's context and in the
conversation transcript, so those fields are replaced with a marker before they
leave the server. See privacy.py.
Setup
Clone alongside the CLI — pyproject.toml expects it as a sibling:
code/
├── nemlig_cli/
└── nemlig-mcp/
git clone https://github.com/eisbaw/nemlig_cli.git
git clone https://github.com/kraenhansen/nemlig-mcp.git
cd nemlig-mcp && uv sync
Credentials come from NEMLIG_USER / NEMLIG_PASS, falling back to the CLI's
~/.config/nemlig/login.json.
Register with Claude
claude mcp add nemlig -- uv --directory /absolute/path/to/nemlig-mcp run nemlig-mcp
Or in .mcp.json:
{
"mcpServers": {
"nemlig": {
"command": "uv",
"args": ["--directory", "/absolute/path/to/nemlig-mcp", "run", "nemlig-mcp"],
"env": { "NEMLIG_USER": "you@example.com", "NEMLIG_PASS": "..." }
}
}
}
Notes on the upstream CLI
Two things this package works around, both worth fixing upstream:
- Progress spinners write to stdout, including from a background thread in
login(). On a stdio MCP server stdout is the JSON-RPC transport, so every CLI call is wrapped in a redirect (_compat.py). Fix: print progress to stderr. - Optional dependencies are declared as required.
opencv-python,pyzbar,Pillow,anthropic,google-api-python-clientandopenfoodfactsare all guarded withtry/except ImportErrorin the code, but listed as hard dependencies, so installing the CLI as a library pulls in all of them. Fix: move them to[project.optional-dependencies].
Development
uv run pytest
The tests make no network calls and need no credentials.
Disclaimer
Not affiliated with nemlig.com. Uses a private API that may change or break, and automated access may conflict with their terms of service.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。