Voltaxion for AI agents and B2B systems.

Three ways to integrate, one commercial surface.

Use direct feeds for ingestion, MCP for agent tooling, or discovery files for automatic capability detection.

Add the MCP server to your agent.

Any client that supports remote MCP servers over Streamable HTTP can connect. No account or API key is needed.

https://mcp.voltaxion.com/mcp

claude mcp add --transport http voltaxion https://mcp.voltaxion.com/mcp

{
  "mcpServers": {
    "voltaxion": { "url": "https://mcp.voltaxion.com/mcp" }
  }
}

curl -sS https://mcp.voltaxion.com/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Anonymous read now. Customer-scoped auth next.

The live posture is conservative: public discovery, public reads and no claim that an indicative quote equals a stock reservation.

Operational limits are explicit.

Cache aggressively, back off on 429 or 503 and retry after a minute, and do not assume the HTML site, data feeds and API share the same threshold.

Start simple, then move up the stack.

Most clients begin with the catalog sample feed, then switch to MCP for structured agent workflows.

curl -sS https://portal.voltaxion.com/data/catalog_sample.json \
  -H "Accept: application/json"

import httpx

url = "https://portal.voltaxion.com/data/catalog_sample.json"

with httpx.Client(timeout=20.0) as client:
    response = client.get(url, headers={"Accept": "application/json"})
    response.raise_for_status()
    payload = response.json()

print(type(payload))
print(payload.keys() if isinstance(payload, dict) else "list payload")

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "search_catalog",
    "arguments": {
      "query": "iPhone 17 Pro Max 256GB",
      "condition": "Brand new",
      "max_price_usd": 1300
    }
  }
}

Use discovery files as the contract index.

Each catalog row carries the VTX SKU, brand, model, storage, colour, condition, Apple model or part number (version), stock, stock location (region), minimum order (moq, moq_label) and unit price in USD. Treat llms.txt as the public map, openapi.json as the API contract and ai-plugin.json as the capability summary.

• llms.txt is the best current human-readable index to integration scope and data intent.
• ai-plugin.json is the right discovery target for agent clients that understand plugin-style capability declarations.
• openapi.json at https://voltaxion.com/.well-known/openapi.json describes the REST API, the JSON feeds and the MCP endpoint.
• Mirror the sample JSON into your own cache instead of hot-linking every request.

Allowed uses are narrow by design.

This is a B2B catalog surface for sourcing workflows and controlled automation.