Custom Agent Integration

Connect any AI agent to QANATIX via MCP or REST.

Option 1: MCP client

Build a custom MCP client that connects to QANATIX's Streamable HTTP endpoint.

Python (using mcp SDK)

from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    async with streamablehttp_client(
        "https://api.qanatix.com/mcp/",
        headers={"Authorization": "Bearer sk_live_abc123..."},
    ) as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()

            # List available tools
            tools = await session.list_tools()
            print([t.name for t in tools.tools])

            # Call search
            result = await session.call_tool(
                "qanatix_search",
                arguments={
                    "vertical": "manufacturing",
                    "query": "M8 bolt stainless",
                    "limit": 5,
                },
            )
            print(result.content[0].text)

TypeScript (using @modelcontextprotocol/sdk)

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const transport = new StreamableHTTPClientTransport(
  new URL("https://api.qanatix.com/mcp/"),
  { requestInit: { headers: { Authorization: "Bearer sk_live_abc123..." } } },
);

const client = new Client({ name: "my-agent", version: "1.0" });
await client.connect(transport);

const result = await client.callTool({
  name: "qanatix_search",
  arguments: { vertical: "manufacturing", query: "M8 bolt", limit: 5 },
});
console.log(result.content);

Option 2: REST API

For agents that don't support MCP, use the REST API directly.

curl -X POST https://api.qanatix.com/api/v1/search/manufacturing \
  -H "Authorization: Bearer sk_live_abc123..." \
  -H "Content-Type: application/json" \
  -d '{"query": "M8 bolt stainless", "limit": 5, "format": "compact"}'

The compact format returns a markdown table optimized for LLM context windows (~120 tokens per result vs ~800 for full JSON).

Tool description for your agent

When registering QANATIX as a tool in your agent framework, use this description:

Search verified enterprise data from QANATIX. Returns ranked, scored results
from the user's private database — not scraped web content. Supports hybrid
search (semantic + keyword + identifier matching). Use for any query about
business data: suppliers, products, compliance, specifications.