🎣 Search business prospects with natural language using Explorium MCP

⚡ 1,211 views · 🎣 Lead Generation & Enrichment

💡 Pro Tip — If you’re pulling LinkedIn data through HTTP requests or dealing with API restrictions, there’s a community node called ScraperNode that handles this natively. It has dedicated scrapers for profiles, companies, jobs, and people search — you just pass a URL and get structured data back.

View All Scrapers

Description

Explorium Prospects Search Chatbot

Template

Download the following json file and import it to a new n8n workflow:

mcp_to_prospects_to_csv.json


Overview

This n8n workflow creates a chatbot that understands natural language requests for finding business prospects and automatically:

Perfect for sales teams, recruiters, and business development professionals who need to quickly find and export targeted prospect lists without learning complex API syntax.

Key Features

Example Queries

The chatbot understands queries like:

Prerequisites

Before setting up this workflow, ensure you have:

  1. n8n instance with chat interface enabled
  2. Anthropic API key for Claude
  3. Explorium API credentials (Bearer token) - Get explorium api key
  4. Basic understanding of n8n chat workflows

Supported Filters

The chatbot can search using these criteria:

Company Filters

Prospect Filters

Installation & Setup

Step 1: Import the Workflow

  1. Copy the workflow JSON from the template
  2. In n8n: Workflows → Add Workflow → Import from File
  3. Paste the JSON and click Import

Step 2: Configure Anthropic Credentials

  1. Click on the Anthropic Chat Model1 node
  2. Under Credentials, click Create New
  3. Add your Anthropic API key
  4. Name: “Anthropic API”
  5. Save credentials

Step 3: Configure Explorium Credentials

You’ll need to set up Explorium credentials in two places:

For MCP Client:

  1. Click on the MCP Client node
  2. Under Credentials, create new Header Auth
  3. Add your authentication header (usually Authorization: Bearer YOUR_TOKEN)
  4. Save credentials

For API Calls:

  1. Click on the Prospects API Call node
  2. Use the same Header Auth credentials created above
  3. Verify the API endpoint is correct

Step 4: Activate the Workflow

  1. Save the workflow
  2. Click the Active toggle to enable it
  3. The chat interface will now be available

Step 5: Access the Chat Interface

  1. Click on the When chat message received node
  2. Copy the webhook URL
  3. Access this URL in your browser to start chatting

How It Works

Workflow Architecture

  1. Chat Trigger: Receives natural language queries from users
  2. Memory Buffer: Maintains conversation context
  3. AI Agent: Interprets queries and generates API parameters
  4. Validation: Checks API structure against Explorium requirements
  5. API Call: Fetches prospect data with pagination
  6. Data Processing: Formats results for CSV export
  7. File Conversion: Creates downloadable CSV file

Processing Flow

User Query → AI Interpretation → Validation → API Call → CSV Export
     ↑                                  ↓
     └──── Error Correction Loop ←──────┘

Validation Rules

The workflow validates:

Usage Guide

Basic Conversation Flow

  1. Start with your query:

    "Find me VPs of Sales at software companies in the US"

  2. Bot processes and responds:

    • Generates API filters
    • Validates the structure
    • Fetches data
    • Returns CSV download link

  3. Refine if needed:

    "Can you also include directors and filter for companies with 100+ employees?"

Query Tips

Advanced Queries

Combine multiple criteria:

"Find engineering managers and senior engineers at B2B SaaS companies 
in New York and California with 50-500 employees and revenue over $5M 
who have been in their role for at least 1 year"

Output Format

The CSV file includes:

Troubleshooting

Common Issues

“Validation failed” errors

No results returned

Chat not responding

Large result sets timing out

Error Messages

The bot provides clear feedback:

Performance Optimization

Best Practices

  1. Start broad, then narrow: Begin with basic criteria and add filters
  2. Use business IDs: When targeting specific companies
  3. Limit by contact info: Add has_email: true for actionable leads
  4. Batch by location: Process regions separately for large searches

API Limits

Customization Options

Modify AI Behavior

Edit the AI Agent system message to:

Extend Functionality

Add nodes to:

Integration Ideas

Security Considerations

Support Resources

For issues with:

🔗 Nodes Used

AI Agent, Anthropic Chat Model, Simple Memory, Structured Output Parser, Convert to File, Chat Trigger

📥 Import

Download workflow.json and import into n8n: Workflow menu → Import from File

📖 Importing guide · 🔑 Credential setup