> ## 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 Crush

> Add Firecrawl web search and scraping to Crush

Connect Firecrawl to Crush as a remote HTTP MCP server, so Crush can search the web and read pages.

## Requirements

* Crush 0.98 or newer.
* A [Firecrawl API key](https://www.firecrawl.dev/app/api-keys), exported as `FIRECRAWL_API_KEY`.

## Quick setup

1. Export your API key in the shell you start Crush from:

```bash theme={null}
export FIRECRAWL_API_KEY="fc-YOUR-API-KEY"
```

2. Add the server to `crush.json` in your project, or to `~/.config/crush/crush.json` for every project:

```json theme={null}
{
  "$schema": "https://charm.land/crush.json",
  "mcp": {
    "firecrawl": {
      "type": "http",
      "url": "https://mcp.firecrawl.dev/v2/mcp",
      "headers": {
        "Authorization": "Bearer $FIRECRAWL_API_KEY"
      }
    }
  }
}
```

3. Start Crush and ask it to search or scrape.

> [accordion] Using a crushrc file?
>
> Newer Crush releases can read a Bash-style `crushrc` file, where an MCP server is one command:
>
> ```bash theme={null}
> mcp add firecrawl \
>   --type http \
>   --url "https://mcp.firecrawl.dev/v2/mcp" \
>   --header Authorization "Bearer $FIRECRAWL_API_KEY"
> ```
>
> Run `crush dirs` to see where Crush looks for configuration on your machine.

See [Configure an API key](https://docs.firecrawl.dev/mcp-server/keyless.md#add-an-api-key) for more on keys.

## Try it

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

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

## What you can do

> [card] [Search](https://docs.firecrawl.dev/features/search.md)
>
> Find current information and read the content of relevant results.

> [card] [Scrape](https://docs.firecrawl.dev/features/scrape.md)
>
> Turn URLs into clean markdown or structured data.

> [card] [Interact](https://docs.firecrawl.dev/features/interact.md)
>
> Navigate, click, and fill forms to reach the data you need.

> [card] [Alexandria](https://docs.firecrawl.dev/features/alexandria.md)
>
> Discover structured data tools, inspect inputs and pricing, then run them through Firecrawl.

## Troubleshooting

* **The server does not start:** check that `FIRECRAWL_API_KEY` is exported in the shell that starts Crush, and that the URL is exactly `https://mcp.firecrawl.dev/v2/mcp`.
* **The header is dropped:** Crush removes a header whose value resolves to an empty string. An unset `FIRECRAWL_API_KEY` causes this.
* **Tools are not used:** some models call MCP tools more reliably than others. Try a different model.


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