# ScraperAPI MCP: Expanded Capabilities

### MCP Server Enhancements <a href="#mcp-server-enhancements" id="mcp-server-enhancements"></a>

Depth: Expanded Tool Coverage

* **Structured Data Endpoints (SDEs)** - Google, Amazon, Walmart, eBay, Redfin now accessible via MCP
* **Crawler Integration** - Full web crawling capabilities through MCP protocol
* All tools callable directly from your preferred AI interface with proper parameter mapping

**Breadth: Multi-Platform Support**

* **Claude Desktop** – Hosted remote MCP server support
* **Claude Code** – Native MCP tool execution
* **Cursor** – Direct MCP integration for agent-driven development
* **Windsurf** – AI-assisted coding with MCP tool access
* **Cline** – Autonomous coding workflows via MCP
* **VSCode + GitHub Copilot** – MCP-enabled tool execution inside VSCode
* **Local Deployment** – Python and Docker support for self-hosted setups
* ​[**n8n Integration**](https://docs.scraperapi.com/integrations/automation-and-workflow-integrations/n8n-integration) – MCP Client Tool support for workflow automation
* **Extended Model Support** – OpenAI and Gemini compatibility ready

#### Claude Skill & Agent Improvements <a href="#claude-skill-and-agent-improvements" id="claude-skill-and-agent-improvements"></a>

**ScraperAPI MCP Skill**

* Intelligent agent guidance for selecting the right tool
* Auto-detects tasks (scraping, searches, crawls, SDE queries)
* Provides best practices for cost, pagination, and output formatting
* Accessible via: `npx skills add scraperapi/scraperapi-skills`

**Enhanced Agent Context**

* Agent now aware of complete ScraperAPI ecosystem
  * n8n node integration suggestions
  * SDK and DataPipeline options
  * Guidance on when to use MCP vs. direct API calls
* Improved decision-making for task optimization

#### What This Means for You <a href="#what-this-means-for-you" id="what-this-means-for-you"></a>

* **Developers**: Direct LLM access to ScraperAPI's full toolkit without manual API calls
* **Teams**: Standardized workflows via skills reduce prompt engineering overhead
* **Scale**: Broader platform support makes integration easier across your tech stack

#### Getting Started <a href="#getting-started" id="getting-started"></a>

1. **Update MCP Server** - `pip install --upgrade scraperapi-mcp-server`
2. **Add Claude Skill** - `npx skills add scraperapi/scraperapi-skills`
3. **Configure Your Client** - Follow tool-specific setup guide (Claude, Cursor, VSCode, etc.)
4. **Start Prompting** - Use natural language to scrape, search, and extract data

#### Documentation & Setup <a href="#get-started-now" id="get-started-now"></a>

<a href="https://docs.scraperapi.com/integrations/llm-integrations/mcp-server" class="button secondary" data-icon="mcp">MCP Server</a><a href="/pages/7YY7dGFNIL9XnKDP6Y94" class="button secondary" data-icon="webhook">MCP Server <--> n8n</a><a href="https://docs.scraperapi.com/integrations/llm-integrations/mcp-server/mcp-skill" class="button secondary">Claude Skill</a>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.scraperapi.com/resources/release-notes/march-2026/scraperapi-mcp-expanded-capabilities.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.