MCP.so
Sign In

CPZAI

@CPZ-Lab

Repository

About CPZAI

CPZAI MCP server. Build, backtest, and deploy quantitative trading strategies from your AI agent. 29 tools: list_strategies, get_strategy, create_strategy, update_strategy, get_backtest_results, list_orders, place_order, list_positions, sync_portfolio, plus dev-time tools. Multi-

#trading#quant#backtesting#algorithmic-trading#python#agent#mcp#finance#portfolio-management#risk-management

Basic information

Category

Finance & Commerce

Transports

stdio

Publisher

CPZ-Lab

Submitted by

Chris

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "cpzai": {
      "url": "https://mcp.cpz-lab.com/mcp",
      "headers": {
        "X-CPZ-Key": "YOUR_KEY",
        "X-CPZ-Secret": "YOUR_SECRET"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is CPZAI?

CPZAI MCP gives AI agents (Claude, Cursor, GPT, or custom builds) read/write access to a quantitative trading platform. It enables natural‑language strategy creation, backtesting, portfolio management, order routing (Alpaca, Interactive Brokers, FIX), and risk computation—all through the agent. The server is designed for quantitative traders and developers who want to interact with their trading infrastructure conversationally.

How to use CPZAI?

  1. Create an API key at ai.cpz-lab.com/settings/api-keys.
  2. Copy the server configuration into your MCP client (e.g., Claude Desktop, Cursor).
  3. Ask your agent a command like “List my strategies and run a 1‑year backtest on the top 3.”

The server validates every tool call individually via the X-CPZ-Key header, with no long‑lived sessions.

Key features of CPZAI

  • 18 tools covering strategy management, backtesting, trading, market data, and risk.
  • Paper‑first safety: live trading requires explicit per‑strategy promotion on the platform.
  • Per‑request API key validation; every tool call re‑authenticates against the platform.
  • User‑scoped data visibility; tools only see data owned by the authenticated key.
  • Open‑source server (MIT) at github.com/CPZ-Lab/cpzai-mcp-server.
  • Free to try at ai.cpz-lab.com.

Use cases of CPZAI

  • Natural‑language strategy development – Describe a trading idea and let the agent create and adjust the strategy.
  • Automated backtesting – Run historical backtests on one or more strategies and review results.
  • Portfolio & order management – Place orders, sync portfolios, list positions, and monitor accounts.
  • Risk monitoring – Compute risk metrics and review historical risk snapshots.
  • Execution & webhook integration – Execute strategies programmatically and manage webhooks to connect external events.

FAQ from CPZAI

What does CPZAI MCP do?

It gives any AI agent read/write access to a quantitative trading platform, enabling strategy creation, backtesting, portfolio management, order routing, and risk computation in natural language.

Is it safe for live trading?

Paper-only is the default. Live trading on a strategy requires explicit promotion inside the platform, not from the agent. Every tool call also re-validates the API key per request, and data is scoped to the authenticated user.

What brokers are supported?

Order routing is supported to Alpaca, Interactive Brokers, and FIX counterparts.

Is the server open source?

Yes. The full source code is available at github.com/CPZ-Lab/cpzai-mcp-server under the MIT license.

How do I get started?

Create a free API key at ai.cpz-lab.com/settings/api-keys, paste the server configuration into your MCP client, and start asking your agent trading tasks.

Comments

More Finance & Commerce MCP servers

AI看线 - A股技术分析与AI预测工具

QuantML-Github

Python-based stock analysis tool that combines traditional technical analysis with AI prediction capabilities. Providing comprehensive stock analysis and forecasting using K-line charts, technical indicators, financial data, and news data. With CMD/WEB/MCP supported.

333

Octagon: MCP for Market Data

OctagonAI

An MCP server for public & prediction markets research. Ask natural-language questions and get structured, source-backed answers across SEC filings, earnings transcripts, company financials, stock & crypto market data, and prediction markets news & research. Built for investors,

142

✅ Official Alpha Vantage MCP Server

calvernaz

A MCP server for the stock market data API, Alphavantage API.

74

Crypto Fear & Greed Index MCP Server

kukapay

Providing real-time and historical Crypto Fear & Greed Index data

53

Financial Modeling Prep MCP (Model Context Protocol)

imbenrabi

A Model Context Protocol (MCP) implementation for Financial Modeling Prep, enabling AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights.

139