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

# MCP Web Search & Scrape in JetBrains AI Assistant

> Add Firecrawl web search and scraping to JetBrains AI Assistant

Add Firecrawl to AI Assistant in IntelliJ IDEA, PyCharm, WebStorm, and the other JetBrains IDEs. AI Assistant starts the Firecrawl MCP server as a local process, using your API key.

## Requirements

* A JetBrains IDE with AI Assistant 2025.1 or newer. MCP client support arrived in that release.
* Node.js 22 or newer on your `PATH`, because the server runs through `npx`.
* A [Firecrawl API key](https://www.firecrawl.dev/app/api-keys).

## Quick setup

1. Open **Settings**, then **Tools**, then **AI Assistant**, then **Model Context Protocol (MCP)**.
2. Select **Add**.
3. Paste this JSON, replace the key, and set **Server level** to global or the current project:

```json theme={null}
{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp@3.33.2"],
      "env": {
        "FIRECRAWL_API_KEY": "fc-YOUR-API-KEY"
      }
    }
  }
}
```

4. Select **OK**, then **Apply**. The **Status** column shows the connection, and its tool icon lists the Firecrawl tools.
5. Enable **Automatically enable new and changed MCP servers** if you want the server to start on its own.

<Accordion title="Use a remote connection instead">
  The current AI Assistant documentation also lists Streamable HTTP servers, configured with a `url` entry in the same JSON. It does not document request headers or a browser sign-in flow, so use the local setup above for Firecrawl unless your IDE shows those options.
</Accordion>

See [Run MCP locally](/mcp-server/local) for the full list of environment variables.

## Try it

```text theme={null}
Search the web for the latest Kotlin release notes and summarize the sources.
```

```text theme={null}
Scrape https://firecrawl.dev and explain what it does.
```

## What you can do

<CardGroup cols={2}>
  <Card title="Search" icon="magnifying-glass" href="/features/search">
    Find current information and read the content of relevant results.
  </Card>

  <Card title="Scrape" icon="file-lines" href="/features/scrape">
    Turn URLs into clean markdown or structured data.
  </Card>

  <Card title="Interact" icon="hand-pointer" href="/features/interact">
    Navigate, click, and fill forms to reach the data you need.
  </Card>

  <Card title="Alexandria" icon="books" href="/features/alexandria">
    Discover structured data tools, inspect inputs and pricing, then run them through Firecrawl.
  </Card>
</CardGroup>

## Troubleshooting

* **The status stays red:** run `node --version` in a terminal and confirm it prints 22 or newer. Restart the IDE after installing Node.js so it sees the new `PATH`.
* **`spawn npx ENOENT`:** the IDE cannot find `npx`. Start the IDE from a shell where `npx` works, or use the full path to `npx` as the command.
* **The server shows `401`:** replace the value of `FIRECRAWL_API_KEY` and select **Apply** again.
* **Logs:** the MCP settings page links to the log folder, which holds one log per server.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.