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

# Set up Firecrawl MCP Server

> Connect Firecrawl, a web scraping platform, as a remote MCP server on the TrueFoundry MCP Gateway so agents can scrape, crawl, map, and extract web content.

[Firecrawl](https://www.firecrawl.dev) is a web scraping platform that turns websites into clean, structured, LLM-ready data. Register its official remote MCP server on the TrueFoundry MCP Gateway so your agents can scrape, crawl, map, search, and extract web content through governed access.

## Using Firecrawl through the MCP Gateway

The [TrueFoundry MCP Gateway](/docs/ai-gateway/mcp/mcp-overview) centralizes access to Firecrawl - agents connect through one endpoint instead of maintaining separate server configurations per client.

When you use Firecrawl MCP server through the AI Gateway, TrueFoundry provides:

* **Authentication** — Clients [authenticate inbound](/docs/ai-gateway/mcp/mcp-gateway-auth-security#inbound-authentication) to the AI Gateway with a Personal Access Token, Virtual Account, or IDE OAuth flow. For outbound access, the AI Gateway injects the configured Firecrawl API key on requests.
* **Tool-level access control** — You can selectively enable or disable individual Firecrawl tools from the TrueFoundry UI.
* **Access control** — [Collaborators and role-based policies](/docs/ai-gateway/mcp/mcp-gateway-auth-security#access-control) define who can use the server and which tools they can invoke. Enable or disable individual Firecrawl tools from the server detail page.
* **Observability** — Tool calls are traced with caller identity, tool name, inputs, and latency. Monitor server- and tool-level usage in [MCP Metrics](/docs/ai-gateway/analytics-mcp-metrics) and export traces to your observability stack via OpenTelemetry.
* **Guardrails** — Apply [pre-tool and post-tool guardrails](/docs/ai-gateway/guardrails-overview) on MCP tool calls.

## Prerequisites

* A TrueFoundry account with permission to add MCP servers.
* A Firecrawl API key. Sign in at [firecrawl.dev](https://www.firecrawl.dev), open the **API Keys** page from the dashboard, and copy your key (it looks like `fc-xxxxxxxx`). Use **Create** to generate a new key if you don't have one yet.

<Frame>
  <img src="https://mintcdn.com/truefoundry/HoY7YPmkj5FoWR9x/images/docs/ai-gateway/firecrawl-api-keys.png?fit=max&auto=format&n=HoY7YPmkj5FoWR9x&q=85&s=716a89dbacf0293d0cf916521f9ad97d" alt="Firecrawl dashboard API Keys page showing the default fc- key and the Create button" width="3838" height="1984" data-path="images/docs/ai-gateway/firecrawl-api-keys.png" />
</Frame>

## Adding Firecrawl MCP server to TrueFoundry

<Steps>
  <Step title="Open the MCP Server catalog">
    Navigate to **MCP Servers** in the TrueFoundry sidebar and click **Add new MCP Server**. On the next screen, select **Connect Official Remote MCP Servers** - this lists official, vetted remote MCP servers that you connect with your own auth.

    <Frame>
      <img src="https://mintcdn.com/truefoundry/HoY7YPmkj5FoWR9x/images/docs/ai-gateway/firecrawl-step1-add-official-remote.png?fit=max&auto=format&n=HoY7YPmkj5FoWR9x&q=85&s=a76863f27425947a7f3597694066009f" alt="Add new MCP Server picker with the Connect Official Remote MCP Servers option highlighted" width="1996" height="1986" data-path="images/docs/ai-gateway/firecrawl-step1-add-official-remote.png" />
    </Frame>
  </Step>

  <Step title="Add Firecrawl">
    Type `firecrawl` in the search box, find **firecrawl** in the catalogue, and click **+ Add**. TrueFoundry opens the Firecrawl MCP server detail page with the server URL pre-filled.

    <Frame>
      <img src="https://mintcdn.com/truefoundry/HoY7YPmkj5FoWR9x/images/docs/ai-gateway/firecrawl-step2-search.png?fit=max&auto=format&n=HoY7YPmkj5FoWR9x&q=85&s=925bcb31fa3ba74b9f6d3b411d151204" alt="MCP server catalog filtered to firecrawl, with the firecrawl card shown" width="1998" height="1984" data-path="images/docs/ai-gateway/firecrawl-step2-search.png" />
    </Frame>
  </Step>

  <Step title="Configure the server">
    TrueFoundry pre-fills the server details for Firecrawl:

    | Field           | Value                                |
    | --------------- | ------------------------------------ |
    | **Name**        | `firecrawl`                          |
    | **Description** | Firecrawl is a web scraping platform |
    | **URL**         | `https://mcp.firecrawl.dev/mcp`      |

    Add **Collaborators** - the users and teams that can use or manage this server - and assign each an **MCP Server Manager** or **MCP Server User** role.

    <Frame>
      <img src="https://mintcdn.com/truefoundry/HoY7YPmkj5FoWR9x/images/docs/ai-gateway/firecrawl-step3-register-form.png?fit=max&auto=format&n=HoY7YPmkj5FoWR9x&q=85&s=a0047ba800755fccc75f9a919c066fa8" alt="Register MCP Server form pre-filled with the firecrawl name, description, URL, and collaborators" width="2002" height="1984" data-path="images/docs/ai-gateway/firecrawl-step3-register-form.png" />
    </Frame>
  </Step>

  <Step title="Authenticate">
    Under **Auth Data**, select **API Key**. Firecrawl authenticates with a static key sent as a request header. Choose how the key is supplied:

    * **Shared Credentials** - one key used by everyone. Enter the actual header value.
    * **Individual Credentials** - each user provides their own key. Use a placeholder (for example `Bearer {{API_KEY}}`) that each user fills in.

    Add a header mapping the name `Authorization` to the value `Bearer fc-<your-firecrawl-key>`, then click **Update MCP Server** to save.

    <Frame>
      <img src="https://mintcdn.com/truefoundry/HoY7YPmkj5FoWR9x/images/docs/ai-gateway/firecrawl-step4-auth-api-key.png?fit=max&auto=format&n=HoY7YPmkj5FoWR9x&q=85&s=624ea46559d558f7eaba3b173b9fda7e" alt="Auth Data section with API Key selected, Shared Credentials chosen, and an Authorization header set to Bearer fc-..." width="1950" height="856" data-path="images/docs/ai-gateway/firecrawl-step4-auth-api-key.png" />
    </Frame>

    <Tip>
      Prefer **Individual Credentials** when each user should bring their own Firecrawl key so usage and rate limits are attributed per user. Use **Shared Credentials** for a single team-wide key.
    </Tip>
  </Step>

  <Step title="Verify tools">
    After saving, the **Tools** tab lists Firecrawl's available tools (scrape, map, crawl, search, extract, and more). Click **Try** on any tool to test it and inspect the JSON output before using it in an agent.

    <Frame>
      <img src="https://mintcdn.com/truefoundry/HoY7YPmkj5FoWR9x/images/docs/ai-gateway/firecrawl-tools-list.png?fit=max&auto=format&n=HoY7YPmkj5FoWR9x&q=85&s=1c15f7dafd8ad2bbdb75cdab8abd9caf" alt="Firecrawl Tools tab showing the available tools such as firecrawl_scrape, firecrawl_map, firecrawl_crawl, firecrawl_search, and firecrawl_extract" width="3496" height="1984" data-path="images/docs/ai-gateway/firecrawl-tools-list.png" />
    </Frame>
  </Step>
</Steps>

## Connecting to an MCP Client

Open the **How To Use** tab on the Firecrawl server detail page for your tenant-specific Gateway URL and ready-to-paste client snippets - don't build the endpoint manually.

The tab includes snippets for Claude Code, VS Code, Claude Web, Claude Desktop, Cursor, Windsurf, Codex, and the Python and TypeScript MCP SDKs. Use **Show API Key** if your client requires a Gateway token in a header.

<Frame>
  <img src="https://mintcdn.com/truefoundry/HoY7YPmkj5FoWR9x/images/docs/ai-gateway/firecrawl-how-to-use.png?fit=max&auto=format&n=HoY7YPmkj5FoWR9x&q=85&s=40a9725d38fd5ec9b5f6ad79974998bb" alt="Firecrawl How To Use tab showing connection commands for multiple MCP clients" width="3510" height="1980" data-path="images/docs/ai-gateway/firecrawl-how-to-use.png" />
</Frame>

## Using the Tool Playground

Before deploying an agent, you can test any Firecrawl MCP server tool directly in TrueFoundry:

<Steps>
  <Step title="Open a tool">
    On the Firecrawl MCP server detail page, click **Try** next to any tool - for example `firecrawl_scrape`.
  </Step>

  <Step title="Fill in the inputs">
    Provide the tool's inputs, such as the `url` of the page to scrape and any format options (for example, `markdown`).
  </Step>

  <Step title="Execute and inspect">
    Click **Execute Tool** and inspect the JSON output in the right panel.
  </Step>
</Steps>

## Tool Metrics

The **Tool Metrics** tab on the Firecrawl server detail page tracks how agents use each tool:

* **Invocation count** - which tools are called most often
* **Latency** - how long each tool takes to respond
* **Error rates** - which tools are failing in production

See [MCP Metrics](/docs/ai-gateway/analytics-mcp-metrics) for server- and tool-level dashboards across your Gateway.

## Disabling Individual Tools

On the **Tools** tab, toggle off any Firecrawl tools your agents don't need:

* **Disabled tools** are hidden from MCP clients and cannot be invoked.
* **Enabled tools** remain available to agents as usual.
