Octoparse MCP Server

by octoparse

5 stars
437 downloads
Not rated
GitHub

About

Official Octoparse MCP server for AI-powered web scraping workflows.

Details

Author
octoparse
GitHub stars
5
Downloads
437
Categories
Other, Web Scraping, Automation

- 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.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Octoparse MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "octoparse mcp server": {
            "octoparse": {
                "url": "https://mcp.octoparse.com"
            }
        }
    }
}

McpServers

{
    "octoparse": {
        "url": "https://mcp.octoparse.com"
    }
}

Octoparse MCP Server

Octoparse
Docs
MCP

English | 日本語

Octoparse MCP Server connects MCP-compatible AI clients to Octoparse so users can discover scraping templates, run cloud extraction tasks, manage existing tasks, and export structured data.

Hosted Server

Use the hosted Streamable HTTP endpoint:

https://mcp.octoparse.com

Configure this as an MCP server endpoint, not as a REST API tool.

Authentication

The hosted server officially supports both OAuth and API key authentication:

- OAuth: the default option when the MCP client can open a browser authorization flow.
- API key: an optional authentication method for clients that can send custom HTTP headers.

For API key mode, send the key in the x-api-key header. Do not place real keys in source control, issue reports, screenshots, or shared logs.

Quick Start

Generic HTTP MCP configuration:

{
  "mcpServers": {
    "octoparse": {
      "type": "http",
      "url": "https://mcp.octoparse.com"
    }
  }
}

Claude OAuth / default authentication:

claude mcp add --transport http octoparse https://mcp.octoparse.com

Claude with API key:

claude mcp add --transport http octoparse https://mcp.octoparse.com --header "x-api-key: YOUR_API_KEY"

Codex CLI:

codex mcp add octoparse --url https://mcp.octoparse.com

Gemini CLI example configuration:

{
  "mcpServers": {
    "octoparse": {
      "httpUrl": "https://mcp.octoparse.com",
      "oauth": {
        "clientId": "Octoparse",
        "enabled": true
      }
    }
  }
}

After adding the server, complete authorization in the browser if your client prompts for OAuth.

More client examples are in Configuration.

Tools

| Tool | Purpose |
| --- | --- |
| search_templates | Find Octoparse templates by keyword, template ID, or slug. |
| execute_task | Validate parameters, create a cloud task, 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. |

See Tools for inputs, examples, and common failure cases.

Typical Workflow

search_templates -> execute_task -> export_data

Example user prompt:

Find a cloud-capable Octoparse template for Amazon product listings, run it for wireless earbuds, and export the result as CSV.

For an existing task, use:

search_tasks -> export_data

Scheduling, notifications, recurring jobs, and external automations are handled by the MCP client or another automation system. The MCP server exposes task and export tools; it does not provide a standalone scheduler.

Scope

Octoparse MCP Server can:

- Search the Octoparse template library.
- Run cloud-capable template tasks.
- Validate template parameters before execution.
- Export collected data when a task has data available.
- Search, start, and stop existing cloud tasks.

It does not:

- Run local-only desktop tasks through the hosted server.
- Create or edit arbitrary custom scraping workflows.
- Upload private templates.
- Provide billing or account administration tools.
- Schedule recurring runs by itself.

Common Limits

- Some templates are local-only and must be run in the Octoparse desktop app.
- Cloud execution depends on account permissions, available credits or quota, target-site availability, and template support.
- Long-running tasks may need follow-up calls. If data is still collecting or exporting, wait and call export_data again.
- Tool availability can be narrowed with includeTools or excludeTools URL parameters. See Overview.

Security

- Keep API keys and OAuth tokens out of Git, logs, screenshots, and public issues.
- Use OAuth when possible for interactive clients.
- Use x-api-key only with clients that store headers securely.
- Report vulnerabilities privately. See Security.

Documentation

- Overview
- Configuration
- Tools
- Troubleshooting
- Octoparse API Docs
- Help Center
- Available on Smithery

Development

npm install
npm run build
npm test

For local environment variables, copy .env.example to .env and fill only values needed for your environment. Never commit .env.

Contributing

Contributions are welcome. Please read CONTRIBUTING.md before opening issues or pull requests.

License

MIT. See LICENSE.md.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.