Connect LiveDataLink to your agent

Claude Desktop / Claude Code JSON config

Add LiveDataLink as an MCP server. Drop this into your Claude Desktop config (or run claude mcp add), restart, and ask Claude to call search_available_datasets to see the live catalog.

{
  "mcpServers": {
    "livedatalink": {
      "url": "https://livedatalink.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Claude Code CLI: claude mcp add --transport http livedatalink https://livedatalink.ai/mcp --header "Authorization: Bearer YOUR_API_KEY". Then ask it to run company_trust_check on a company name.

Raw Streamable-HTTP MCP client curl / JSON-RPC 2.0

No framework needed. The endpoint speaks MCP over Streamable HTTP, so any client that can POST JSON-RPC works. This calls the free discovery tool directly.

curl -X POST https://livedatalink.ai/mcp \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Accept: application/json, text/event-stream" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "search_available_datasets",
      "arguments": { "query": "trucking safety" }
    }
  }'

search_available_datasets is free and costs no credits. Swap in tools/list to fetch the live, machine-readable inventory of all 284 tools.

LangChain Python

Use langchain-mcp-adapters to load every LiveDataLink tool as LangChain tools, then hand them to any agent.

# pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
    "livedatalink": {
        "transport": "streamable_http",
        "url": "https://livedatalink.ai/mcp",
        "headers": {"Authorization": "Bearer YOUR_API_KEY"},
    }
})

# All 284 tools, ready for your agent
tools = await client.get_tools()

CrewAI Python

MCPServerAdapter from crewai-tools connects over Streamable HTTP and exposes the tools to your crew.

# pip install 'crewai-tools[mcp]'
from crewai_tools import MCPServerAdapter

server_params = {
    "url": "https://livedatalink.ai/mcp",
    "transport": "streamable-http",
    "headers": {"Authorization": "Bearer YOUR_API_KEY"},
}

with MCPServerAdapter(server_params) as tools:
    # Pass tools to an Agent; e.g. it can now call company_trust_check
    print([t.name for t in tools])

Vercel AI SDK TypeScript

experimental_createMCPClient wires the endpoint into the AI SDK, so generateText / streamText can call the tools.

// npm i ai @modelcontextprotocol/sdk
import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const mcpClient = await createMCPClient({
  transport: new StreamableHTTPClientTransport(
    new URL("https://livedatalink.ai/mcp"),
    { requestInit: { headers: { Authorization: "Bearer YOUR_API_KEY" } } }
  ),
});

// Spread these into the tools option of generateText / streamText
const tools = await mcpClient.tools();