Exploring Deployments with AI

This page is currently being developed. Check back soon for complete documentation.

Coming Soon

This how-to guide will cover:

• Installing and configuring AI tools that integrate with MCP servers (VS Code, Cursor, Claude, ChatGPT, Replit, etc.)

• Connecting your AI tool to the Environment MCP Server

• Finding the Environment MCP Server endpoint from your deployment

• Authenticating with your Datafye environment

• Exploring available datasets conversationally

• Querying market data for specific symbols and time periods

• Analyzing backtest scorecards with AI assistance

• Comparing multiple backtest runs to identify improvements

• Monitoring deployed algo health and positions

• Debugging common deployment issues interactively

• Example conversations and use cases

• Multi-server setup (using both Environment and SDK MCP servers)

What You'll Need

Before following this guide, ensure you have:

• Any Datafye deployment - Foundry or Trading (features available based on what's deployed in your environment)

• AI tool that integrates with MCP servers - VS Code, Cursor, Claude, ChatGPT, Replit, or any other MCP-compatible tool

• Environment MCP Server endpoint - Displayed when you provision your deployment with datafye foundry provision or datafye trading provision

Overview

The Environment MCP Server runs within your provisioned Datafye deployment and provides your AI tool with real-time access to:

• Your data cloud datasets and schemas (available in all scenarios)

• Market data flowing through your environment (available in all scenarios)

• Backtest results and scorecards (if Algo Container is deployed)

• Deployed algo configurations and state (if Algo Container is deployed)

• Broker connectivity and trading status (if Broker Connector is deployed)

• Environment health and status (available in all scenarios)

By connecting your AI tool to this server, you can explore and debug your deployment conversationally instead of manually querying APIs or reading logs.

Need Help Now?

While we finalize this documentation, you can:

• Understand the concept — Environment MCP Server explains what it is and how it works

• Provision a deployment — Choose Your Path to provision any Datafye environment with the MCP server

• Learn about MCP protocol — Model Context Protocol official documentation

• Learn SDK coding — Vibe Coding Algos with AI for SDK-focused AI assistance

---

Last updated: 2025-10-23