Octoparse MCP Server

What is Octoparse MCP Server?

Octoparse MCP Server connects MCP-compatible AI clients to Octoparse, enabling users to discover scraping templates, run cloud extraction tasks, manage existing tasks, and export structured data. It is for users who want to automate web scraping via AI assistants.

How to use Octoparse MCP Server?

Configure the hosted Streamable HTTP endpoint URL https://mcp.octoparse.com as an MCP server in your client. Authentication is via OAuth (default, browser-based) or API key (sent in the x-api-key header). Example JSON configuration for generic HTTP MCP, or CLI commands for Claude, Codex CLI, and Gemini are provided.

Key features of Octoparse MCP Server

• Hosted Streamable HTTP endpoint, no local installation required.
• Supports OAuth and API key authentication.
• Search the Octoparse template library by keyword, ID, or slug.
• Create, start, and stop cloud extraction tasks.
• Export collected data as JSON, CSV, Excel, HTML, or XML.
• Validate template parameters before task execution.

Use cases of Octoparse MCP Server

• Search for a scraping template and run it on target data.
• Start or stop an existing cloud task from an AI assistant.
• Export task results in desired format after extraction completes.
• Automate data collection by integrating with MCP-compatible clients.

FAQ from Octoparse MCP Server

What does Octoparse MCP Server do vs alternatives?

It connects AI clients to Octoparse's cloud extraction and template library, offering hosted server and built-in task management tools.

What are the runtime/dependency requirements?

Only an MCP-compatible client is needed. The server is hosted, so no local Octoparse installation or Node.js is required for end users.

Where does my data live?

Data is processed and stored in Octoparse’s cloud. Exported data is delivered via the export_data tool.

What are known limits?

Some templates are local-only (not runnable via the server). Cloud execution depends on account permissions, credits, and target site availability. Long-running tasks may require follow-up calls.

How does authentication work?

The server supports OAuth (default) and API key authentication. For API key mode, send the key in the x-api-key header.