Octoparse MCP server
{
"mcpServers": {
"octoparse": {
"type": "http",
"url": "https://mcp.octoparse.com"
}
}
}{
"mcpServers": {
"octoparse": {
"type": "http",
"url": "https://mcp.octoparse.com"
}
}
}{
"mcpServers": {
"octoparse": {
"type": "http",
"url": "https://mcp.octoparse.com"
}
}
}{
"servers": {
"octoparse": {
"type": "http",
"url": "https://mcp.octoparse.com"
}
}
}{
"mcpServers": {
"octoparse": {
"type": "http",
"url": "https://mcp.octoparse.com"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0
What it does
Octoparse MCP Server connects AI clients to Octoparse web scraping service, enabling discovery of scraping templates, creation and management of cloud-based extraction tasks, and export of collected data. It is for developers and AI applications that need to integrate web scraping capabilities without building custom extraction logic.
- Search the Octoparse template library by keyword or template ID to find a preset scraper matching your target website.
- Execute a cloud task from a preset template with custom parameters to extract structured data from a website.
- Export collected data from completed tasks in formats like JSON, CSV, Excel, HTML, or XML.
Tools this server exposes
| Tool | Does |
|---|---|
| search_templates | Find Octoparse templates by keyword, template ID, or slug. |
| execute_task | Validate parameters, create a cloud task from an Octoparse preset template, and start extraction. |
| export_data | Export task results as JSON, CSV, Excel, HTML, or XML when data is ready. |
| search_tasks | Search existing tasks in the authenticated account. |
| start_or_stop_task | Start or stop an existing cloud task by task ID. |
| redeem_coupon_code | Redeem a promotion, coupon, or resource code supplied by the user. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.