Octoparse MCP Server
Enables AI assistants to perform no-code web scraping via Octoparse. Users can describe data to extract, create and control scraping tasks, and export results as JSON or CSV.
README
Octoparse MCP Server
Turn any website into structured data — just by asking your AI assistant.
Octoparse MCP connects AI tools like Claude, ChatGPT, and Cursor to Octoparse, the no-code web scraping platform. No coding. No browser automation scripts. Just describe what you want.
What can you do with it?
You: "Scrape the top 100 Amazon search results for 'wireless earbuds' and save as CSV"
AI: Task created and started... Done. 100 products exported to earbuds.csv
You: "Track iPhone 16 prices on Best Buy every day this week"
AI: Scheduled. I'll run the task daily and notify you of any price changes.
You: "Find all job postings for 'data analyst' on LinkedIn posted in the last 7 days"
AI: Searching templates... Task running... 340 listings exported.
No scraping experience needed. If you can describe the data you want, Octoparse MCP can get it.
Common use cases
- 🛒 E-commerce — Monitor competitor prices, track stock availability
- 📈 Market research — Collect reviews, ratings, and product listings at scale
- 💼 Recruiting — Aggregate job postings from multiple platforms
- 📰 Media monitoring — Archive news articles and track topics over time
- 🏠 Real estate — Pull listings, prices, and location data automatically
Quick Start
Cursor / VS Code / Other clients
{
"mcpServers": {
"octoparse": {
"url": "https://mcp.octoparse.com"
}
}
}
Claude Desktop
claude mcp add octoparse -s user -t http https://mcp.octoparse.com
Gemini CLI (~/.gemini/settings.json)
{
"mcpServers": {
"octoparse": {
"httpUrl": "https://mcp.octoparse.com",
"oauth": { "clientId": "Octoparse", "enabled": true }
}
}
}
After adding the server, complete OAuth authorization in your browser when prompted.
For ChatGPT and step-by-step guides for all clients, see the Full Setup Guide.
What's included
| 🔍 Search Templates | Ready-to-use scraping templates for popular sites |
| 📋 Create Tasks | Set up new scraping jobs via natural language |
| ▶️ Control Tasks | Start, stop, and monitor execution |
| 💾 Export Data | Download results as JSON or CSV |
| 👤 Account Info | Check credits and subscription status |
Requirements
- An Octoparse account (no credit card required to start)
- An MCP-compatible AI client (Claude, ChatGPT Plus/Team/Enterprise, Cursor, Gemini CLI, VS Code, etc.)
Resources
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.