> ## 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 Cloudflare MCP Server Portals

> Add Firecrawl web scraping and search to a Cloudflare One MCP server portal

Add Firecrawl's hosted MCP server to a [Cloudflare One MCP server portal](https://developers.cloudflare.com/cloudflare-one/access-controls/ai-controls/mcp-portals/) so your team reaches Firecrawl's search and scrape tools through one portal URL with your Access policies.

## Quick setup

[Create a Firecrawl API key](https://www.firecrawl.dev/app/api-keys). Then add Firecrawl as an MCP server in Cloudflare Access with the portal API, using the key as a bearer credential:

```bash theme={null}
export CLOUDFLARE_ACCOUNT_ID=your-cloudflare-account-id
export CLOUDFLARE_API_TOKEN=your-cloudflare-api-token
export FIRECRAWL_API_KEY=fc-YOUR_API_KEY

curl -X POST "https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/access/ai-controls/mcp/servers" \
  -H "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Firecrawl",
    "hostname": "https://mcp.firecrawl.dev/v2/mcp",
    "auth_type": "bearer",
    "auth_credentials": "'"$FIRECRAWL_API_KEY"'"
  }'
```

The portal sends `auth_credentials` to Firecrawl as `Authorization: Bearer <key>`. You can also add the server in the Cloudflare dashboard under **Zero Trust** > **Access controls** > **MCP Portals** > **MCP servers** > **Add MCP server**, using the same URL.

Next, add the server to a portal, attach Access policies that decide who sees it, and choose the tools to expose. Cloudflare's [MCP server portals guide](https://developers.cloudflare.com/cloudflare-one/access-controls/ai-controls/mcp-portals/) covers creating the portal.

## Try it

Connect an MCP client to your portal URL (`https://<subdomain>.<domain>/mcp`), then ask:

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

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

## Troubleshooting

* **The server shows a sync or authentication error:** check that the key is valid and that `auth_type` is `bearer`; update the server's credentials if you rotated the key.
* **Firecrawl's tools are missing in the portal:** the portal exposes only the tools an admin selected for it, so review the portal's tool list.
* **Users cannot see Firecrawl:** the server link appears only for users who match an Allow policy on the server.


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