> ## 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 Amazon Q Developer

> Add Firecrawl web search and scraping to Amazon Q Developer in your IDE

Connect Firecrawl to Amazon Q Developer in VS Code, JetBrains, and other supported IDEs through the hosted MCP server. Q Developer opens a browser so you can sign in with your Firecrawl account.

<Note>
  The Amazon Q Developer CLI is now the Kiro CLI. For terminal use, follow the [Kiro setup](/quickstarts/kiro).
</Note>

## Quick setup

1. Open your IDE, then the Q Developer panel, then the **Chat** panel.
2. Select the tools icon, then the plus (+) button.
3. Choose a scope: **global** stores the server in `~/.aws/amazonq/default.json`, and **local** stores it in `.amazonq/default.json` in the project.
4. Enter `firecrawl` as the name, choose **http** as the transport, and enter this URL:

```text theme={null}
https://mcp.firecrawl.dev/v2/mcp-oauth
```

5. Select **Save**. Q Developer opens a browser page for you to authorize access. Sign in to Firecrawl and approve the connection.
6. Review each tool's permission (**Ask**, **Always allow**, or **Deny**) in the panel that appears after saving.

<Accordion title="Prefer to edit the configuration file?">
  Q Developer also reads MCP servers from `~/.aws/amazonq/mcp.json` (global) and `.amazonq/mcp.json` (project):

  ```json theme={null}
  {
    "mcpServers": {
      "firecrawl": {
        "url": "https://mcp.firecrawl.dev/v2/mcp-oauth"
      }
    }
  }
  ```

  Support for the `mcp.json` files is controlled by the `useLegacyMcpJson` field in `default.json`, which is `true` by default.
</Accordion>

<Accordion title="Prefer an API key?">
  In the same dialog, add a header named `Authorization` with the value `Bearer fc-YOUR-API-KEY` and use `https://mcp.firecrawl.dev/v2/mcp` as the URL. See [Configure an API key](/mcp-server/keyless#add-an-api-key).
</Accordion>

See the [OAuth connection guide](/mcp-server/oauth) for more details.

## Try it

```text theme={null}
Search the web for the latest AWS SDK for Python 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

* **A "Fix Configuration" alert appears:** select it to return to the form and check the URL.
* **The browser page does not open:** choose **Edit setup** for the server, save again, and complete the authorization when the page opens.
* **The server is listed but its tools do not run:** open the server in the MCP Servers panel and confirm it is enabled and the tools are not set to **Deny**.
* **Two Firecrawl entries:** a server in `.amazonq/default.json` takes precedence over the global one. Remove the duplicate you do not want.


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