Octoparse Connector for AI agents.
8 live capabilities
Manage cloud web scraping and data extraction tasks through conversation.
Waiting for input…
Why people use Octoparse
Octoparse for Automated Web Scraping & Data Extraction
This Connector changes that by putting the controls in your chat. You can tell your agent to start a scraper, check the status, and pull the results into your workspace in one go. You get to skip the dashboard entirely and move straight to the analysis.
What Vinkius changes
You get a conversational interface for your entire cloud scraping pipeline.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Competitive Price Tracking
A business analyst asks the agent to start the 'Daily Retailer' scraper and summarize any price drops over 10% from the latest data.
- Real-world use case 02
Lead Generation
A growth hacker tells the agent to run a LinkedIn scraper and immediately format the results into a CSV-ready markdown table.
- Real-world use case 03
Schema Debugging
A data engineer asks the agent to list all tasks and then pull a sample of the JSON data to verify the fields match the database.
Complete set · 8capabilities
The complete Octoparse capability set.
These are the exact actions your AI can choose when you ask it to work with Octoparse.
01—04
4 capabilities in this set.
Part of 8 available through Octoparse.
- 01 Capability
Stop task
Stop a running cloud task immediately. Use this to halt a crawler if it's behaving unexpectedly or no longer needed.
- 02 Capability
Get task status
Check the current running status of any cloud task. Use this to see if your bots are still active or finished.
- 03 Capability
List task groups
List all task groups and folders in your account. Use these IDs to filter which scraping tasks the AI should look at.
- 04 Capability
List tasks
List all configured cloud scraping tasks. This helps the agent see every available project you have set up.
05—08
4 capabilities in this set.
Part of 8 available through Octoparse.
- 05 Capability
Get new data
Get new (non-exported) data from a task
- 06 Capability
Get task data
Export data from a completed scraping task using offset-based pagination. This lets you pull the actual results into your AI's context.
- 07 Capability
Start task
Start a cloud scraping task instantly. This tells the engine to begin fetching data from your target websites.
- 08 Capability
Update data status
Mark data as exported
Set up in minutes
One URL. Then ask Octoparse to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Octoparse from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_YNVzYKGdUzzshKHx6wuFcnKCq4KAE2d7CRRCVwit/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Octoparse, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Octoparse for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_YNVzYKGdUzzshKHx6wuFcnKCq4KAE2d7CRRCVwit/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Octoparse URL.
- Step 03
Save and start
Save the connection and enable Octoparse in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"octoparse": {
"url": "https://edge.vinkius.com/vk_preview_YNVzYKGdUzzshKHx6wuFcnKCq4KAE2d7CRRCVwit/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Octoparse
Open Agent mode in chat and ask: "Using Octoparse, help me...". 8 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"octoparse": {
"url": "https://edge.vinkius.com/vk_preview_YNVzYKGdUzzshKHx6wuFcnKCq4KAE2d7CRRCVwit/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Octoparse
Ask Copilot: "Using Octoparse, help me...". 8 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"octoparse": {
"url": "https://edge.vinkius.com/vk_preview_YNVzYKGdUzzshKHx6wuFcnKCq4KAE2d7CRRCVwit/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Octoparse
Open Cascade and ask: "Using Octoparse, help me...". 8 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"octoparse": {
"url": "https://edge.vinkius.com/vk_preview_YNVzYKGdUzzshKHx6wuFcnKCq4KAE2d7CRRCVwit/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Octoparse
Ask Cline: "Using Octoparse, help me...". 8 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add octoparse --transport http "https://edge.vinkius.com/vk_preview_YNVzYKGdUzzshKHx6wuFcnKCq4KAE2d7CRRCVwit/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Octoparse
Ask Claude: "Using Octoparse, show me...". 8 tools are ready
Where the request belongs
Work Octoparse can move forward.
This is for the data person who's tired of dashboard fatigue. It's for anyone who spends too much time switching between browser tabs to see if a crawler finished or to copy-paste results into a spreadsheet.
Data Engineer
Automates the checking of extraction states and pulls JSON samples to debug schemas without leaving the terminal.
Growth Hacker
Spins up scrapers for Amazon or LinkedIn to build email lists on the fly.
Business Analyst
Fetches competitive pricing matrices overnight and asks the AI to highlight price drops in the chat.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsOctoparse
Scrape data from any website visually with a no-code web scraper that handles pagination, login, and JavaScript rendering.
Olostep
Scrape web pages at scale with a headless browser API that renders JavaScript and returns clean structured data instantly.
Spider
High-performance Rust-powered web scraping and crawling. scrape, crawl, and search up to 100K+ pages/second with built-in anti-bot protection.
ScrapingBee
Powerful web scraping with JS rendering, premium proxies, and AI-powered data extraction directly from your AI agent.
ZenRows
Scrape HTML, bypass anti-bots, and extract structured data using ZenRows' advanced proxy and browser network.
Scrapfly
Scrape web data at scale with a managed API that handles proxies, browser rendering, and anti-bot bypassing automatically.
Bring your own AI
Change the model, client or framework. Keep Octoparse connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Octoparse.
The practical details behind the request, access and result.
Can I use Octoparse MCP to start scrapers automatically?
Yes, you can tell your agent to trigger any of your existing cloud tasks instantly. This removes the need to manually click buttons in the Octoparse dashboard.
How do I get the scraped data into my chat?
The Connector pulls the results directly from Octoparse into your conversation so you can see them immediately. You can then ask the agent to summarize, format, or analyze that data.
Can I check if my scrapers are still running?
You can ask the agent for the status of any specific task to see if it's active, finished, or pending. It provides real-time updates on your cloud tasks.
Does Octoparse MCP work with my current account?
Yes, it connects to your existing Premium Octoparse account using your API credentials. It works with the projects and tasks you have already set up.
Can I change the search URL without opening the dashboard?
Yes, the agent can update your task parameters like URLs or keywords on the fly. This is great for quickly pivoting your scraping targets.
Is it possible to clear my test data?
You can ask the agent to purge the data from a specific task to keep your production environment clean. It helps you keep your results organized and accurate.
Can I have my AI format the scraped JSON into a clean Markdown table?
Absolutely. Because Octoparse MCP connects natively via the get_task_data capability directly into the AI's isolated context window, the language model can instantly translate cumbersome JSON fields into polished, structured, and legible tabular outputs on demand.
Is it possible to track task progress percentage in the chat?
Yes. When you instruct your agent to run get_task_status, it fetches the real-time runtime progress metrics from Octoparse's cloud. You'll see whether it's Waiting, Running, or Completed, along with how many rows have been extracted so far.
Do I need a paid Octoparse plan for API capabilities to work?
Yes. Octoparse explicitly limits their Advanced Cloud APIs strictly to their paid subscription levels. A Free tier account will reject the authentication tokens when attempting to fetch the runtime data.
Can my AI automatically find the latest extracted data for a specific task?
Yes! Use the get_not_exported_data capability with the Task ID. Your agent will respond with complete metadata for the newest records that haven't been marked as exported yet in seconds.
How do I find my Octoparse OpenAPI Access Token?
Log in to Octoparse, navigate to the OpenAPI section in your profile or developer portal, and follow the instructions to generate a Bearer token using your account credentials.
Can I start a scraper via the AI?
Absolutely. Use the start_task capability with your Task ID. The AI will command Octoparse to begin the extraction in the cloud immediately.
One connection away
Give your agent a direct line to Octoparse.
Connect Octoparse once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available