Coming Soon — Deploying soon

Connect Your AI Agent to
True Market Intelligence

14 live data sources. Cross-exchange signals, whale detection, arbitrage, and prediction markets — compressed into ~300-token context packets. Connect your favourite AI tools in under 2 minutes.

>“Any whale activity on BTC in the last hour?”
←3 whale buys on Binance — $4.2M total, strong accumulation at $67,400
Get StartedRead the Docs
14
Live Data Sources
12
Crypto Exchanges
~300
Tokens / Symbol
<1ms
Analytics Latency
The Problem

Raw Exchange Data Wastes Your Context Window

AI agents spend most of their token budget parsing verbose JSON instead of reasoning about market conditions.

Without Market.ai

Every exchange speaks a different format. A single orderbook snapshot consumes 10,000+ tokens of nested arrays and metadata.

  • -10,000+ tokens for one orderbook snapshot
  • -12 different JSON schemas to parse
  • -No cross-exchange aggregation
  • -No signal detection or anomaly alerts
Raw Exchange Data
10,000+
tokens / symbol

With Market.ai

One normalized API delivers pre-digested context packets. Price action, orderbook intelligence, cross-exchange signals — all in ~300 tokens.

  • +~300 tokens per symbol, fully analyzed
  • +One unified schema across all exchanges
  • +Cross-exchange aggregation + arb detection
  • +10 signal types with severity levels
Market.ai Context
~300
tokens / symbol
Why Market.ai

Intelligence No Single Exchange Can Provide

Cross-exchange signals, AI-native delivery, semantic search, and natural language narratives. The market intelligence layer your AI agent is missing.

Market Intelligence

Cross-Exchange Signals

10 signal types no single exchange can show: whale movements across venues, liquidation cascades, cross-exchange funding spikes, orderbook imbalances, and more. Rolling-window anomaly detection with severity levels.

Arbitrage Detection

Real-time cross-exchange price divergence across 14 venues. Spot arb opportunities by spread in basis points with exact exchange pair and direction.

Polymarket Predictions

Crypto Up/Down probabilities for BTC, ETH, SOL, and XRP across 5-minute to daily timeframes. A real-time sentiment signal no exchange provides.

AI-Native Delivery

MCP Server

Not just an API — a Model Context Protocol server. Your AI gets market intelligence as native tool calls. 10,000+ tokens of raw data compressed into ~300-token context packets.

Natural Language Narratives

Every data point comes with a human-readable narrative. "BTC rallying +2.1%, strong buy pressure (OBI 0.23), 42.5 BTC bid wall at 67k." Your AI reads context, not raw numbers.

AI Chat

Talk to the market. Ask questions, get analysis, execute trades, and query your portfolio — all through natural language. Available on web, Discord, and Telegram.

Search & History

Semantic Search

"Find patterns similar to last BTC liquidation cascade." Vector-powered search over historical signals and narratives. Your AI agent can query the past to understand the present.

Historical Replay

Replay past market conditions at 1x–10x speed for backtesting AI agents. Same data format as live — your agent doesn't need different parsing logic.

Webhook Alerts

Push signals to Discord, Slack, Telegram, or any HTTP endpoint. Filter by signal type, severity, and symbol. Never miss a whale move or liquidation cascade.

Works With Every Platform

Bring Your Own AI

Market.ai is an MCP server. Connect Claude, ChatGPT, Gemini, or any MCP-compatible client — your AI gets live market intelligence as native tool calls. No custom integration code.

Claude

Native MCP support in Claude Desktop and Claude Code

ChatGPT

Connect via REST API, WebSocket, or MCP bridge

Gemini

Google AI with Market.ai context via MCP

OpenClaw

Autonomous trading agents with built-in market intelligence

Any MCP Client

Cursor, Windsurf, custom agents — anything that speaks MCP

API

One Request, Complete Market Context

A single API call returns everything your AI agent needs — in ~300 tokens instead of 10,000+.

Request
curl -H "Authorization: Bearer mk_live_YOUR_KEY" \
  https://api.market-ai.dev/v1/quotes/BTC/USDT
MCP — Claude Desktop Config
{
  "mcpServers": {
    "market-ai": {
      "url": "https://mcp.market-ai.dev/sse",
      "headers": {
        "Authorization": "Bearer mk_live_YOUR_KEY"
      }
    }
  }
}
Response — ~300 tokens
{
  "ok": true,
  "data": {
    "sym": "BTC/USDT",
    "px": 67452.31,
    "chg": 2.14,
    "vol": "1.2B",
    "obi5": 0.23,
    "spread": 0.8,
    "walls": {
      "bid": [{"px": 67000, "qty": "42.5", "x": 8.2}]
    },
    "xchg": [
      {"n": "binance", "px": 67451.80, "vol": "485M"},
      {"n": "coinbase", "px": 67453.10, "vol": "312M"},
      {"n": "bybit", "px": 67452.00, "vol": "198M"}
    ],
    "trend": "Bullish",
    "narrative": "BTC rallying +2.1%, strong buy pressure (OBI 0.23), 42.5 BTC bid wall at 67000 (8.2x median)."
  }
}
Three Delivery Layers

Choose How You Connect

REST for one-off queries, WebSocket for live feeds, MCP for AI agents, or natural language chat for everyone.

1
Data Access

REST API & WebSocket

On-demand queries or real-time push. Get quotes, orderbooks, signals, funding rates, and klines via REST. Subscribe to live channels via WebSocket for instant updates.

2
AI-Native

MCP Server

Native Model Context Protocol server. Your AI agent calls tools like get_market_context, get_signals, or search_historical — receiving pre-digested, token-efficient intelligence directly.

3
Conversational

AI Chat

Natural language interface. Ask questions, get market analysis, execute trades, and query Polymarket — all through conversation. Works on web, Discord, and Telegram.

Under the Hood

How It Works

Raw exchange data flows through a Rust analytics engine, gets stored in Redis and a vector database, then is served to your AI in the format it needs.

12 Exchanges + NASDAQ + Polymarket
Rust Core Engine

Direct WebSocket connections to 12 crypto exchanges + NASDAQ + Polymarket. No CCXT, no third-party aggregators. Sub-millisecond orderbook analytics, cross-exchange aggregation, and anomaly detection — all in Rust for maximum throughput.

Redis Bridge

Pub/Sub for real-time broadcasts, Streams for durable event logs, TimeSeries for OHLCV candle storage, and Hashes for latest state. The high-speed bridge between ingestion and delivery.

Vector Database

Every signal, narrative, and market event is embedded into Qdrant. Semantic search lets your AI agent ask "what happened last time BTC funding spiked above 0.1%?" and get contextually relevant historical matches.

Your AI Agent — ~300 tokens per symbol
Data Sources

14 Exchanges, One Unified Feed

Direct WebSocket connections to every major exchange. No CCXT. No third-party aggregators. Pure, unfiltered market data.

BinanceBinanceCoinbaseCoinbaseBybitBybitOKXOKXKrakenKrakenKuCoinKuCoinBitfinexBitfinexBinanceBinanceCoinbaseCoinbaseBybitBybitOKXOKXKrakenKrakenKuCoinKuCoinBitfinexBitfinex
Gate.ioGate.ioMEXCMEXCHTXHTXdYdXdYdXHyperliquidHyperliquidAlpacaAlpacaPolymarketPolymarketGate.ioGate.ioMEXCMEXCHTXHTXdYdXdYdXHyperliquidHyperliquidAlpacaAlpacaPolymarketPolymarket
Ecosystem

Plugins & Extensions

Native integrations for the tools you already use. Market intelligence directly in your development and trading workflow.

Coming Soon

Claude Code

Market.ai as a native Claude Code skill. Query signals, analyze orderbooks, and get market context without leaving your terminal.

Coming Soon

OpenClaw

Market.ai plugin for OpenClaw agents. Autonomous trading agents with built-in market intelligence and signal-driven decision making.

Available Now

REST & WebSocket API

Direct API access for custom integrations. Real-time WebSocket push for live data, REST for queries. Build anything with raw market intelligence.

Connect Your AI to Live Markets

Get your API key and start receiving market intelligence in under two minutes. MCP, REST, WebSocket, or Chat — pick your layer.

Get StartedRead the Docs