Real-time Extract of Job, Company, Salary Details via Bright Data MCP & OpenAI

Notice Community nodes can only be installed on self-hosted instances of n8n.

Who this is for

This workflow automates the real-time extraction of Job Descriptions and Salary Information from job listing pages using Bright Data MCP and analyzes content using OpenAI GPT-4o mini.

This workflow is ideal for:

Recruiters & HR Tech Startups**: Automate job data collection from public listings

Market Intelligence Teams**: Analyze compensation trends across companies or geographies

Job Boards & Aggregators**: Power search results with structured, enriched listings

AI Workflow Builders**: Extend to other career platforms or automate resume-job match analysis

Analysts & Researchers**: Track hiring signals and salary benchmarks in real time

What problem is this workflow solving?

Traditional scraping of job portals can be challenging due to cluttered content, anti-scraping measures, and inconsistent formatting. Manually analyzing salary ranges and job descriptions is tedious and error-prone.

This workflow solves the problem by:

Simulating user behavior using Bright Data MCP Client to bypass anti-scraping systems

Extracting structured, clean job data in Markdown format

Using OpenAI GPT-4o mini to analyze and extract precise salary details and refined job descriptions

Merging and formatting the result for easy consumption

Delivering final output via webhook, Google Sheets, or file system

What this workflow does

Components & Flow

Input Nodes job_search_url: The job listing or search result URL

job_role: The title or role being searched for (used in logging/formatting)

MCP Client Operations MCP Salary Data Extractor

Simulates browser behavior and scrapes salary-related content (if available)

MCP Job Description Extractor

Extracts full job description as structured Markdown content

OpenAI GPT-4o mini Nodes

Salary Information Extractor

Uses GPT-4o mini to detect, clean, and standardize salary range data (if any)

Job Description Refiner

Extracts role responsibilities, qualifications, and benefits from unstructured text

Company Information Extractor

Uses Bright Data MCP and GPT-4o mini to extract the company information

Merge Node Combines the refined job description and extracted salary information into a unified JSON response object

Aggregate node Aggregates the job description and salary information into a single JSON response object

Final Output Handling

The output is handled in three different formats depending on your downstream needs:

Save to Disk**

Output stored with filename including timestamp and job role

Google Sheet Update**

Adds a new row with job role, salary, summary, and link

Webhook Notification**

Pushes merged response to an external system

Pre-conditions

Knowledge of Model Context Protocol (MCP) is highly essential. Please read this blog post - model-context-protocol You need to have the Bright Data account and do the necessary setup as mentioned in the Setup section below. You need to have the Google Gemini API Key. Visit Google AI Studio You need to install the Bright Data MCP Server @brightdata/mcp You need to install the n8n-nodes-mcp

Setup

Please make sure to setup n8n locally with MCP Servers by navigating to n8n-nodes-mcp Please make sure to install the Bright Data MCP Server @brightdata/mcp on your local machine. Sign up at Bright Data. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. Create a Web Unlocker proxy zone called mcp_unlocker on Bright Data control panel. In n8n, configure the OpenAi account credentials. In n8n, configure the credentials to connect with MCP Client (STDIO) account with the Bright Data MCP Server as shown below.

Make sure to copy the Bright Data API_TOKEN within the Environments textbox above as API_TOKEN=<your-token>

How to customize this workflow to your needs

Modify Input Source

Change the job_search_url to point to any job board or aggregator

Customize job_role to reflect the type of jobs being analyzed

Tweak LLM Prompts (Optional)

Refine GPT-4o mini prompts to extract additional fields like benefits, tech stacks, remote eligibility

Change Output Format

Customize the merged object to output JSON, CSV, or Markdown based on downstream needs

Add additional destinations (e.g., Slack, Airtable, Notion) via n8n nodes