Overview

AI Hub Overview

Use 6MM from AI clients and agentic workflows through CLI, MCP, hosted market data, and workflow templates.
View as Markdown

6MM Agentic AI Hub is the AI-native interface for 6MM market data, account workflows, and future controlled trading operations.

Instead of switching between dashboards, API docs, and scripts, users can ask an AI client to query 6MM, explain market conditions, review account risk, or prepare an order preview. The AI client does not replace the 6MM API security model; it calls structured 6MM tools through CLI, MCP, or workflow templates.

What you can ask an AI client

Use AI Hub when you want to ask questions such as:

Show me the BTC-USDT-PERP order book and explain current liquidity.
Compare BTC and ETH funding rates over the last 24 hours.
Check my testnet positions and explain liquidation risk. Do not place orders.
Preview a small BTC long order and explain fees, margin impact, and risk checks.

Why AI Agents need a dedicated access layer

AI Agents work best when they have structured tools instead of raw webpages or unstructured copied text. AI Hub gives them:

Requirement6MM approach
Live market contextPublic market-data tools and resources for symbols, order books, trades, funding, fees, and rules.
Clear permissionsSeparate public data, account-read, preview, and controlled trading scopes.
Safer executionPreview-first order flow, explicit confirmation, idempotency, limits, and audit logs.
Client flexibilityHosted MCP, Local MCP, CLI, Remote MCP, and Agentic Skills for different AI environments.

What AI Hub includes

6MM CLI

Command-line access for terminals, scripts, and coding agents that can execute shell commands.

Local MCP

Run a local MCP server so AI clients can call 6MM tools while user credentials stay on the local machine.

Hosted MCP

Connect to a 6MM-hosted MCP endpoint for zero-install public market data and rule context.

Agentic Skills

Reusable workflow templates for market analysis, portfolio review, liquidation protection, and execution planning.

Setup paths

PathBest forUser should know
Hosted MCPQuick public market-data accessNo install and no user API key for public data. Trading is not the first-release goal.
Local MCPAI clients that need private account contextThe MCP server runs locally and credentials remain on the user’s machine.
CLICoding agents, scripts, and terminal usersProduces agent-friendly command output and can be used without an MCP server.
Remote MCPInstitutions and teams that want their own endpointThe user or institution controls hosting, credentials, network access, and logs.
Agentic SkillsRepeatable workflowsSkills guide the AI through analysis and risk steps using approved tools.

What is available first

AI Hub should start with public market data and trading-rule resources:

  • Markets.
  • Tickers.
  • Order books.
  • Trades.
  • Klines.
  • Funding rates.
  • System status.
  • Fees, contract specs, margin rules, and risk rule resources.

Private account access and trading should be staged:

  • Account-read tools require explicit read-only credentials.
  • Order preview should come before any real order creation.
  • Controlled trading requires permission scopes, service-side risk checks, user confirmation, idempotency, and audit logs.

Start here

Choose a Setup

Pick the right path based on your AI client, security needs, and deployment model.

AI Client Guides

Start with ChatGPT Desktop, Claude Desktop, Claude Code, Codex CLI, Cursor, Gemini CLI, VS Code, or Windsurf.

Hosted MCP

Start with public market data without installing a local server.

Local MCP

Use a local server when private account context or future trading tools are needed.