ATOM Pricing Intelligence

What Is This?

ATOM MCP Server lets any MCP-compatible AI agent (Claude, GPT, Cursor, Windsurf, VS Code Copilot) query real-time AI inference pricing data programmatically. Think of it as the Bloomberg Terminal for AI pricing, accessible via the Model Context Protocol.

Ask your AI assistant a question like "What's the cheapest way to run GPT-4o?" and it calls ATOM's tools behind the scenes, returning a data-backed answer from 1,600+ pricing SKUs across 40+ vendors globally.

Built by ATOM (A7OM) — the world's first methodological inference pricing index.

AIPI Indexes

14 benchmark indexes across four categories:

All indexes are global (GLB), calculated weekly using chained matched-model methodology to eliminate composition bias.

Tools

Pricing Tiers

Free tier (no API key): Enough to understand the market — counts, ranges, distributions, benchmarks.

ATOM MCP Pro ($49/mo): Full granular data — every vendor, model, price, and spec. → a7om.com/mcp

Quick Start

Option 1: Remote URL — Claude.ai / Claude Desktop (recommended)

No install required. Connect directly to ATOM's hosted server:

Claude.ai (web): Settings → Connectors → Add custom connector

Name: ATOM Pricing Intelligence
URL:  https://atom-mcp-server-production.up.railway.app/mcp

Claude Desktop: Settings → Developer → Edit Config

{
  "mcpServers": {
    "atom-pricing": {
      "url": "https://atom-mcp-server-production.up.railway.app/mcp"
    }
  }
}

Note: Remote URL support requires a recent Claude Desktop version. If it doesn't work, use the npx method below.

Claude Desktop (via npx proxy):

{
  "mcpServers": {
    "atom-pricing": {
      "command": "npx",
      "args": ["mcp-remote", "https://atom-mcp-server-production.up.railway.app/mcp"]
    }
  }
}

Option 2: Local (stdio) — for Cursor, Windsurf, etc.

git clone https://github.com/A7OM-AI/atom-mcp-server.git
cd atom-mcp-server
npm install && npm run build

Add to your MCP client config:

{
  "mcpServers": {
    "atom-pricing": {
      "command": "node",
      "args": ["/path/to/atom-mcp-server/dist/index.js"],
      "env": {
        "SUPABASE_URL": "https://jonncmzxvxzwyaznokba.supabase.co",
        "SUPABASE_ANON_KEY": "your-anon-key"
      }
    }
  }
}

Option 3: Deploy your own (Railway)

Set environment variables in Railway dashboard:

• SUPABASE_URL
• SUPABASE_ANON_KEY
• ATOM_API_KEYS (comma-separated, for paid tier validation)
• TRANSPORT=http

Example Queries

Once connected, just ask your AI assistant naturally:

• "What's the cheapest way to run GPT-4o?"
• "Compare Claude Sonnet 4.5 pricing across all vendors"
• "Find open-source text models under $0.50 per million tokens"
• "Show me Google's full model catalog"
• "What are the AIPI benchmark prices for text inference?"
• "How do neocloud prices compare to cloud marketplaces?"
• "How much cheaper is open-source inference?"
• "Give me a market overview of AI inference pricing"
• "What are the key market KPIs for AI inference?"

Environment Variables

Tech Stack

• TypeScript / Node.js
• MCP SDK (@modelcontextprotocol/sdk)
• Supabase (PostgreSQL) via REST API
• Express (HTTP transport)
• Zod (schema validation)

About ATOM

ATOM tracks 1,600+ AI inference pricing SKUs from 40+ vendors globally through the AIPI (ATOM Inference Price Index) system — the first methodological price benchmark for AI inference. 14 indexes span modality, channel, tier, and licensing dimensions, updated weekly using chained matched-model methodology to eliminate composition bias.

Vendors are classified across four distribution channels: Model Developers (direct API), Cloud Marketplaces (AWS Bedrock, Google Vertex, Azure), Inference Platforms (DeepInfra, Fireworks, Together AI), and Neoclouds (Groq, Cerebras).

Products: ATOM MCP · ATOM Terminal · ATOM Feed

License

MIT