---
title: "MCP Server"
description: "The QuantConnect Model Context Protocol (MCP) server is a bridge that connects a Large Language Model to the QuantConnect API."
canonical: https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server
markdown: https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server.md
language: python
source: https://github.com/QuantConnect/Documentation/tree/master/09%20AI%20Assistance/08%20MCP%20Server
modified: 2026-10-22
index: https://www.quantconnect.com/llms.txt
---

# MCP Server

[Documentation](https://www.quantconnect.com/docs/v2.md) > [AI Assistance](https://www.quantconnect.com/docs/v2/ai-assistance.md) > MCP Server

> Code examples are shown in Python. Append `?lang=csharp` to this URL for the C# version of this page.

The QuantConnect Model Context Protocol (MCP) server is a bridge that connects a Large Language Model (LLM) to the [QuantConnect API](https://www.quantconnect.com/docs/v2/cloud-platform/api-reference.md). With this setup, you can prompt the LLM and have it interact with our API on your behalf. This server equips the LLM with tools to create projects, run backtests, deploy live algorithms, and more. Our MCP integration can supercharge your existing workflow on QuantConnect and can even unlock quant trading to non-programmers. Simply prompt the LLM in layperson language and let it do the heavy lifting for you.

[Video](https://player.vimeo.com/video/1114056119)

The following MCP clients are officially supported for the QC MCP Server. To view all the third-party clients that work with MCP, see the [Feature support matrix](https://modelcontextprotocol.io/clients#feature-support-matrix) on the MCP website. Clients that operate from the terminal can edit files on your local machine and can run from the terminal in Visual Studio Code.

- [Key Concepts](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/key-concepts.md): Introduction to our MCP Server
- [Claude Code](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/claude-code.md): Claude via a terminal or Local Platform
- [Copilot](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/copilot.md): GPT, Claude, or Gemini via Local Platform
- [Cursor](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/cursor.md): Various models via an IDE
- [Devin Desktop](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/devin-desktop.md): Various models via an IDE

## Pages in This Section

- [Key Concepts](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/key-concepts.md): The QuantConnect Model Context Protocol (MCP) server is a bridge that a Large Language Model to the QuantConnect API.
- [Claude Code](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/claude-code.md): Claude Code is command line utility that can connect Claude to the QuantConnect MCP Server.
- [Copilot](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/copilot.md): Copilot is an AI coding assistant that can connect various Large Language Models (LLM) to the QuantConnect MCP Server.
- [Cursor](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/cursor.md): Cursor is an AI coding assistant that can connect various Large Language Models (LLM) to the QuantConnect MCP Server.
- [Devin Desktop](https://www.quantconnect.com/docs/v2/ai-assistance/mcp-server/devin-desktop.md): Devin Desktop is an AI coding assistant that can connect various Large Language Models (LLM) to the QuantConnect MCP Server.