What are the prerequisites to run the server?
Python 3.11+, Interactive Brokers Gateway installed and running, and an IB account with API access enabled.
@karimQuant
基本情報
Interactive Brokers API Multi-Client Protocol Server
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"ibapi-mcp-server": {
"command": "python",
"args": [
"server.py"
]
}
}
}Retrieve your current portfolio positions and account summary
A middleware server that connects to Interactive Brokers Gateway and exposes its functionality through the FastMCP framework, allowing LLMs like Claude to interact with your IB account, retrieve portfolio information, and potentially execute trades.
Install prerequisites (Python 3.11+, IB Gateway running, IB account with API access), then start the server using python server.py (stdio), python server.py sse (SSE), or fastmcp run server.py. For development with a testing environment, use fastmcp dev server.py. Connect client applications like Claude Desktop to the server.
Python 3.11+, Interactive Brokers Gateway installed and running, and an IB account with API access enabled.
Run `python server.py` for stdio transport, `python server.py sse` for SSE, or `python server.py sse port=9000` for a custom port. Alternatively, use the FastMCP CLI: `fastmcp run server.py` or `fastmcp dev server.py`.
The server provides a `get_portfolio_tool` to retrieve your current portfolio positions and account summary.
It connects to the Interactive Brokers Gateway via the official IB API.
The server supports stdio and SSE (Server-Sent Events) transport. SSE can be used with a custom port if desired.

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

directree MCP server — query the honest software directory from any AI assistant

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu
コメント