Back to Tools

lum-deep-search

Deep web research with multi-source analysis, fact-checking, and LLM-powered synthesis

1 Tools Available
https://lum-deep-search.lum.tools/mcp

API Key Required

Create an API key to get ready-to-use IDE configuration snippets with your credentials pre-filled.

Create API Key

Quick start

Cursor configuration

File: .cursor/mcp.json 

{
  "mcpServers": {
    "lum-deep-search": {
      "url": "https://lum-deep-search.lum.tools/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY_HERE"
      }
    }
  }
}

Installation Steps:

  1. 1 Open Cursor settings
  2. 2 Navigate to MCP Servers configuration
  3. 3 Add the configuration above to .cursor/mcp.json
  4. 4 Restart Cursor to load the MCP server

⚠️ Replace YOUR_API_KEY_HERE with your actual API key after creating one.

VSCode configuration

File: .vscode/mcp.json 

{
  "mcpServers": {
    "lum-deep-search": {
      "url": "https://lum-deep-search.lum.tools/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY_HERE"
      }
    }
  }
}

Installation Steps:

  1. 1 Install an MCP extension from the VSCode marketplace
  2. 2 Create .vscode/mcp.json in your project
  3. 3 Paste the configuration above
  4. 4 Reload VSCode window

⚠️ Replace YOUR_API_KEY_HERE with your actual API key after creating one.

Windsurf configuration

File: .windsurf/mcp.json 

{
  "mcpServers": {
    "lum-deep-search": {
      "url": "https://lum-deep-search.lum.tools/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY_HERE"
      }
    }
  }
}

Installation Steps:

  1. 1 Open Windsurf settings
  2. 2 Navigate to MCP configuration
  3. 3 Add the configuration above
  4. 4 Restart Windsurf

⚠️ Replace YOUR_API_KEY_HERE with your actual API key after creating one.

Claude Desktop configuration

File: claude_desktop_config.json 

{
  "mcpServers": {
    "lum-deep-search": {
      "url": "https://lum-deep-search.lum.tools/mcp",
      "transport": "http",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY_HERE"
      }
    }
  }
}

Installation Steps:

  1. 1 Open Claude Desktop settings
  2. 2 Navigate to Developer → MCP Settings
  3. 3 Add the configuration above to your config file
  4. 4 Restart Claude Desktop

⚠️ Replace YOUR_API_KEY_HERE with your actual API key after creating one.

Python SDK configuration

File: example.py 

import httpx
import json

# Configuration
SERVER_URL = "https://lum-deep-search.lum.tools/mcp"
API_KEY = "YOUR_API_KEY_HERE"

async def call_tool(tool_name: str, arguments: dict):
    """Call an MCP tool"""
    async with httpx.AsyncClient() as client:
        response = await client.post(
            SERVER_URL,
            json={
                "jsonrpc": "2.0",
                "method": "tools/call",
                "params": {
                    "name": tool_name,
                    "arguments": arguments
                },
                "id": 1
            },
            headers={
                "Authorization": f"Bearer {API_KEY}",
                "Content-Type": "application/json",
                "Accept": "application/json, text/event-stream"
            }
        )
        
        # Handle SSE response
        content = response.text
        if "event: message" in content:
            for line in content.split('\n'):
                if line.startswith('data: '):
                    return json.loads(line[6:])
        
        return response.json()

# Example usage
import asyncio
result = asyncio.run(call_tool("search", {"query": "Python async", "num_results": 3}))
print(result)

Installation Steps:

  1. 1 Install httpx: pip install httpx
  2. 2 Copy the code above
  3. 3 Replace YOUR_API_KEY_HERE with your actual API key
  4. 4 Run the script

⚠️ Replace YOUR_API_KEY_HERE with your actual API key after creating one.

cURL configuration

File: test.sh 

#!/bin/bash
# List available tools
curl -X POST "https://lum-deep-search.lum.tools/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer YOUR_API_KEY_HERE" \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'

# Call a tool (example: search)
curl -X POST "https://lum-deep-search.lum.tools/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer YOUR_API_KEY_HERE" \
  -d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"search","arguments":{"query":"test","num_results":3}},"id":1}'

Installation Steps:

  1. 1 Copy the commands above
  2. 2 Replace YOUR_API_KEY_HERE with your actual API key
  3. 3 Run in your terminal
  4. 4 Use jq to pretty-print JSON: ... | jq '.'

⚠️ Replace YOUR_API_KEY_HERE with your actual API key after creating one.

Available Tools

deep_search

Perform deep multi-source research with comprehensive analysis. Searches for multiple sources, analyzes top sources, and synthesizes findings.

query*

Example Usage

deep_search

curl -X POST "https://lum-deep-search.lum.tools/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "deep_search",
      "arguments": {
        
        
        "query": "..."
        
        
      }
    },
    "id": 1
  }'
View full documentation

Ready to integrate?

Create your API key to unlock all 1 tools

Create API Key Now