> ## Documentation Index
> Fetch the complete documentation index at: https://developers.scrapeunblocker.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Code Plugin

> Install ScrapeUnblocker into Claude Code with two commands - MCP tools, a /scrape-url command, and reference skills, with your key stored in the OS keychain.

The official **Claude Code plugin** gives [Claude Code](https://claude.com/claude-code) everything it needs to read pages that block it: the MCP tools, a one-shot `/scrape-url` command, and reference material it pulls in when writing scraping code for your project.

You bring your **own** API key. It is entered once, when the plugin is enabled, and stored in your operating system's keychain - not in a settings file, not in an environment variable.

## Install

Run both commands inside Claude Code:

```
/plugin marketplace add ScrapeUnblocker/claude-code-plugin
/plugin install scrapeunblocker@scrapeunblocker
```

Claude Code asks for your API key while enabling the plugin. Get one from the [dashboard](https://app.scrapeunblocker.com) if you don't have it yet.

## What you get

**MCP tools** - Claude calls these on its own whenever a page is blocked or needs a real browser:

| Tool            | What it does                                            |
| --------------- | ------------------------------------------------------- |
| `fetch_html`    | Fetch the fully rendered HTML of any URL.               |
| `fetch_parsed`  | Fetch a page and return AI-parsed structured JSON.      |
| `google_search` | Run a Google search and return organic results as JSON. |

**Command** - for when you want an explicit one-off fetch:

```
/scrapeunblocker:scrape-url https://example.com
/scrapeunblocker:scrape-url https://example.com parsed
/scrapeunblocker:scrape-url https://example.com country=US
```

**Skills** - reference material loaded on demand while Claude writes code against the API:

| Skill            | Covers                                                  |
| ---------------- | ------------------------------------------------------- |
| `best-practices` | Endpoints, parameters, retries, choosing the right call |
| `page-source`    | Rendered HTML, render waits, country targeting          |
| `parsed-data`    | Structured extraction and how to fix a bad parse        |

## Example prompts

* "Read `https://example-shop.com/product/123` and tell me the price." - Claude reaches for `fetch_html` by itself once the page blocks a plain request.
* "Get the parsed data for `https://www.amazon.com/dp/B08N5WRWNW` and summarise the product."
* "Write me a Python script that scrapes these 40 listing URLs." - Claude pulls in the skills and writes it against the SDK, with retries and country targeting handled properly.

## Managing the plugin

| Command                                             | What it does              |
| --------------------------------------------------- | ------------------------- |
| `/plugin configure scrapeunblocker@scrapeunblocker` | Change the stored API key |
| `/plugin update scrapeunblocker`                    | Pull the latest version   |
| `/plugin uninstall scrapeunblocker@scrapeunblocker` | Remove it                 |

## Plugin or MCP server?

Both run the same server underneath, so the tools are identical.

|                     | Plugin                             | [MCP server](/sdks/mcp)                                   |
| ------------------- | ---------------------------------- | --------------------------------------------------------- |
| Setup               | Two commands, key prompted for you | Add the server config, set `SCRAPEUNBLOCKER_KEY` yourself |
| Where the key lives | OS keychain                        | Environment variable or config file                       |
| Extras              | `/scrape-url` command, skills      | Tools only                                                |
| Works in            | Claude Code                        | Claude Code, Claude Desktop, claude.ai, any MCP client    |

Use the plugin in Claude Code; use the MCP server everywhere else.

## Source

* GitHub: [ScrapeUnblocker/claude-code-plugin](https://github.com/ScrapeUnblocker/claude-code-plugin)
* The bundled server is the same npm package: [`scrapeunblocker-mcp`](https://www.npmjs.com/package/scrapeunblocker-mcp)