MCP Integration Guide

What is MCP?

The Model Context Protocol (MCP) allows AI assistants like Claude to directly interact with aidata.market. Your AI can search for datasets, evaluate quality, and make purchases autonomously within the budget limits you configure.

MCP Endpoint

All MCP requests use JSON-RPC 2.0 over HTTPS with Bearer token authentication.

Claude Desktop Configuration

Add the following to your Claude Desktop MCP configuration file:

{
  "mcpServers": {
    "aidata-market": {
      "url": "https://api.aidata.market/mcp/v1",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with an API key from your API Keys page.

cURL Example

curl -X POST https://api.aidata.market/mcp/v1 \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "search_datasets",
      "arguments": {
        "query": "NLP training data",
        "format": "json",
        "min_quality": "cleaned",
        "max_price_cents": 10000
      }
    },
    "id": 1
  }'

Python Example

import httpx

MCP_ENDPOINT = "https://api.aidata.market/mcp/v1"
API_KEY = "YOUR_API_KEY"

# Search for datasets
response = httpx.post(
    MCP_ENDPOINT,
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json",
    },
    json={
        "jsonrpc": "2.0",
        "method": "tools/call",
        "params": {
            "name": "search_datasets",
            "arguments": {
                "query": "sentiment analysis",
                "format": "csv",
                "min_quality": "labeled",
            },
        },
        "id": 1,
    },
)

result = response.json()
print(result)