Can the AI place real trades?
No – due to a Trading212 API restriction, orders can only be created in practice (demo) mode. The live environment is supported for all other operations.
@lukeplausin
基本信息
A Model Context Protocol (MCP) connector tool for interfacing agentic AI with the Trading212 broker
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-trading212": {
"command": "uv",
"args": [
"--directory",
"path/to/project",
"run",
"--api-key",
"<KEEP_THIS_SECRET>",
"--environment",
"demo",
"mcp-server-trading212",
"--host",
"127.0.0.1",
"--port",
"6677",
"--sse"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
This server connects agentic AI to a Trading212 brokerage account, allowing the AI to analyse portfolios, suggest stocks, manage investment pies, and perform account queries. It is designed for users who want to give an AI controlled access to their Trading212 account while respecting aggressive API rate limits through caching.
Install via uv or Docker and configure it in claude_desktop_config.json by specifying the Trading212 API key and environment (demo or live). For remote hosting, the server can run in SSE mode behind a reverse proxy. Example configuration uses uv run with --api-key and --environment flags, or the Docker image can be built and run.
No – due to a Trading212 API restriction, orders can only be created in practice (demo) mode. The live environment is supported for all other operations.
The server caches API responses in‑memory for 5 minutes by default. If a local Redis server is running on port 6379, the server will automatically use it instead of the in‑memory cache.
Always test on the demo account first. If hosting remotely, use a reverse proxy with HTTPS and ideally Mutual TLS. Avoid storing the API key in plaintext; consider a secret manager.
The server supports the standard STDIO transport (used with Claude Desktop) and SSE (Server‑Sent Events) mode for running as an HTTP service.
It is released under the MIT License. By using it you agree to the license terms, which include indemnity from any financial losses resulting from its use.

Model Context Protocol Servers
A curated list of references for MLOps
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Open-source MCP to use Blender with any LLM
评论