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

# LiteLLM

> Expose ScrapeGraphAI to any model through the LiteLLM MCP gateway

## Overview

[LiteLLM](https://docs.litellm.ai/) ships a built-in [MCP gateway](https://docs.litellm.ai/docs/mcp) that lets the LiteLLM Proxy connect to Model Context Protocol servers and surface their tools to any model you route through it. ScrapeGraphAI is available as a first-party MCP server, so a single config entry gives every LiteLLM client access to smart scraping, web crawling, search scraping, and agentic scraping workflows.

LiteLLM ships ScrapeGraph in its default [`mcp_servers.json`](https://github.com/BerriAI/litellm/blob/main/mcp_servers.json), pointing at the [ScrapeGraph MCP server](https://github.com/ScrapeGraphAI/scrapegraph-mcp) hosted on [Smithery](https://smithery.ai/).

<CardGroup cols={2}>
  <Card title="LiteLLM MCP docs" icon="book" href="https://docs.litellm.ai/docs/mcp">
    How LiteLLM connects to MCP servers
  </Card>

  <Card title="ScrapeGraph MCP server" icon="github" href="https://github.com/ScrapeGraphAI/scrapegraph-mcp">
    The MCP server LiteLLM connects to
  </Card>
</CardGroup>

## Prerequisites

* A [ScrapeGraphAI API key](https://dashboard.scrapegraphai.com/) — set as `SGAI_API_KEY`
* LiteLLM installed with proxy extras:

```bash theme={null}
pip install 'litellm[proxy]'
```

## Configure the MCP server

Add ScrapeGraph to the `mcp_servers` block of your LiteLLM proxy config. This is the same entry LiteLLM ships in its default `mcp_servers.json` — the Smithery-hosted server exposes both HTTP and SSE transports.

```yaml config.yaml theme={null}
model_list:
  - model_name: gpt-5
    litellm_params:
      model: openai/gpt-5
      api_key: os.environ/OPENAI_API_KEY

mcp_servers:
  scrapegraph:
    url: "https://smithery.ai/api/mcp/scrapegraph-mcp"
    description: "Smart scraping, web crawling, search scraping, and agentic scraping workflows."
```

The raw `mcp_servers.json` entry added in LiteLLM looks like this:

```json mcp_servers.json theme={null}
{
  "scrapegraph": {
    "http_url": "https://smithery.ai/api/mcp/scrapegraph-mcp",
    "sse_url": "https://smithery.ai/api/mcp/scrapegraph-mcp/sse",
    "description": "The ScrapeGraph MCP server provides programmatic access to ScrapeGraph AI's web scraping capabilities, including smart scraping, web crawling, search scraping, and agentic scraping workflows."
  }
}
```

<Note>
  The ScrapeGraph MCP server reads your ScrapeGraphAI API key from `SGAI_API_KEY`. Set it in the environment where the proxy runs, or pass it through the Smithery config of your MCP server deployment.
</Note>

## Start the proxy

```bash theme={null}
export OPENAI_API_KEY="your-openai-key"
export SGAI_API_KEY="your-scrapegraph-key"

litellm --config config.yaml
```

The proxy boots on `http://localhost:4000` and registers the ScrapeGraph tools under the MCP gateway.

## List the available tools

LiteLLM exposes connected MCP tools over its MCP endpoint. Point any MCP-aware client at `http://localhost:4000/mcp` to discover them:

```bash theme={null}
curl -s http://localhost:4000/mcp \
  -H "Authorization: Bearer $LITELLM_API_KEY"
```

The ScrapeGraph server registers these tools:

| Tool                          | What it does                                                         |
| ----------------------------- | -------------------------------------------------------------------- |
| `scrape`                      | Fetch a page as markdown, HTML, links, or a screenshot               |
| `extract`                     | Extract structured JSON from a URL with a prompt and optional schema |
| `search`                      | Search the web and return ranked results                             |
| `crawl_start`                 | Start an async multi-page crawl                                      |
| `crawl_get_status`            | Poll a crawl job's progress                                          |
| `crawl_stop` / `crawl_resume` | Control an active crawl                                              |
| `schema`                      | Generate or augment a JSON Schema from a prompt                      |
| `monitor_*`                   | Create, list, pause, resume, and inspect scheduled jobs              |
| `credits`                     | Check remaining account credits                                      |
| `history`                     | View paginated request history                                       |

## Use it from a model

With the gateway running, any model routed through LiteLLM can call the ScrapeGraph tools during a completion. Pass the proxy's MCP tools through your client of choice:

```python theme={null}
import openai

client = openai.OpenAI(
    base_url="http://localhost:4000",
    api_key="sk-1234",  # your LiteLLM proxy key
)

response = client.responses.create(
    model="gpt-5",
    input="Scrape https://scrapegraphai.com and summarize what the product does.",
    tools=[
        {
            "type": "mcp",
            "server_label": "scrapegraph",
            "server_url": "http://localhost:4000/mcp",
            "require_approval": "never",
        }
    ],
)

print(response.output_text)
```

The model decides when to call `scrape`, `search`, or `extract`, receives the structured result, and writes its final answer from the scraped data.

## Support

<CardGroup cols={2}>
  <Card title="GitHub Issues" icon="github" href="https://github.com/ScrapeGraphAI/scrapegraph-mcp/issues">
    Report bugs and request features
  </Card>

  <Card title="Discord Community" icon="discord" href="https://discord.gg/uJN7TYcpNa">
    Get help from our community
  </Card>
</CardGroup>