# QuantConnect

A hosted MCP server for QuantConnect that lets an AI assistant open projects, edit strategies, run backtests and deploy from the chat.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: quantconnect
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/quantconnect/mcp-server
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/quantconnect

## What it does

Nothing gets installed on your machine. Your MCP client talks to `https://www.quantconnect.com/api/v2/mcp`, you approve access for your QuantConnect organization in the browser, and the platform tools land in the conversation. The agent can then open the current project, start new ones, change strategy files, run backtests, tune parameters, and send a strategy to paper or live trading.

Registering it in the Claude terminal takes one command: `claude mcp add --transport http quantconnect https://www.quantconnect.com/api/v2/mcp`. After that run `/mcp`, pick quantconnect, finish the browser flow. The Claude extension for VS Code picks the server up inside a Local Platform project, and `/mcp` confirms the connection.

Billing is the real gate. Only a paid agent node (A1-1, A4-8 or A16-32) can connect, while the free A-MICRO node is turned away. Check what your organization actually has before editing any client config.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Install**
- The MCP registry has no launch command for it: see the repository README

## When to use it
- open the current project and explain the strategy behind it
- generate a Python strategy file and fix it after a failed backtest
- run a backtest and condense the output into a short summary
- sweep strategy parameters and report the best values
- move a finished strategy into paper trading

## Example prompts
- Open the current project and walk me through the strategy logic.
- Sweep the strategy parameters and show me which values performed best.

## Similar
- [strategy-pivot-designer](https://affpapa.org/en/nevibecode/skills/strategy-pivot-designer.md) — skill · 3700 installs
- [strategy-compare](https://affpapa.org/en/nevibecode/skills/strategy-compare.md) — skill · 2400 installs
- [manifoldbt-backtester](https://affpapa.org/en/nevibecode/skills/manifoldbt-backtester.md) — skill · 2000 installs
- [strategy-framework](https://affpapa.org/en/nevibecode/skills/strategy-framework.md) — skill · 569 installs
- [llmquant-options](https://affpapa.org/en/nevibecode/skills/llmquant-options.md) — skill · 517 installs
- [backtesting-arena](https://affpapa.org/en/nevibecode/mcp/backtesting-arena.md) — MCP server · 9340 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
