# Firecrawl MCP server

> Search the web and scrape pages or files into clean markdown or structured JSON for LLM use.

- Listing: https://mcp.tc/i/firecrawl
- Connect: use the server's own URL `https://mcp.firecrawl.dev/v2/mcp` (sign-in optional); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: optional (works without sign-in)
- Category: [Search & Web Data](https://mcp.tc/c/search-web)
- Vendor: Firecrawl
- Homepage: <https://docs.firecrawl.dev/mcp-server>
- Repository: <https://github.com/firecrawl/firecrawl-mcp-server>
- Package: npm `firecrawl-mcp`

## About

Firecrawl connects an assistant to the Firecrawl web data service. The keyless hosted endpoint can search the web, scrape a single URL into markdown, HTML, links, screenshots or JSON that matches a schema, and parse local documents such as PDF, Word and spreadsheet files. Search also has categories for developer content (GitHub issues, pull requests, READMEs, docs) and research literature.

It runs as a hosted streamable HTTP endpoint at mcp.firecrawl.dev/v2/mcp, or locally through the firecrawl-mcp npm package. Keyless use has usage limits. Signing in with OAuth or sending an API key as a bearer token raises the limits and, depending on plan, adds tools such as map, crawl and agent.

## What it can do

- Scrape a URL into markdown, HTML, links or screenshots
- Extract JSON that matches a supplied schema from a page
- Search web, news or image sources with ranked results
- Search indexed GitHub issues, pull requests and docs for coding questions
- Filter search to research-affiliated sites for biomedical and arXiv papers
- Parse PDF, Word, RTF and spreadsheet files into markdown or JSON
- Map and crawl sites with an API key or OAuth sign-in

## Tools (3)

- `firecrawl_scrape`: Scrape one URL and return markdown, HTML, links, screenshots or JSON matching a schema. (read-only)
- `firecrawl_search`: Search web, news or image sources and return ranked results with highlights. (read-only)
- `firecrawl_parse`: Parse a supported document such as PDF, Word or spreadsheet into markdown or JSON. (read-only)

## Example prompts

- "Scrape https://example.com/pricing and return it as markdown"
- "Search the web for recent news on solid-state batteries"
- "Extract product names and prices from this page as JSON"
- "Find GitHub issues describing this error message"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp
```

2. Start Claude Code and type `/mcp`. **firecrawl** should show as connected. To sign in for more access, pick it and choose **Authenticate**.

Add `--scope user` to make it available in every project, not just this one. Works without a key. An API key from Firecrawl raises the limits: send it as `Authorization: Bearer <YOUR_API_KEY>`.

### Claude Desktop

1. Open **Settings → Connectors** and click **Add custom connector**.

2. Name it **Firecrawl** and paste this URL:

```url
https://mcp.firecrawl.dev/v2/mcp
```

3. Click **Add**, then **Connect**. Signing in to Firecrawl is optional.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Firecrawl&connectorUrl=https%3A%2F%2Fmcp.firecrawl.dev%2Fv2%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://mcp.firecrawl.dev/v2/mcp` and click **Add**.

3. Click **Connect**. Signing in to Firecrawl is optional.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://mcp.firecrawl.dev/v2/mcp` as the server URL and choose **No authentication**, or **OAuth** to sign in to Firecrawl for more access.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=firecrawl&config=eyJ1cmwiOiJodHRwczovL21jcC5maXJlY3Jhd2wuZGV2L3YyL21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "firecrawl": {
      "url": "https://mcp.firecrawl.dev/v2/mcp"
    }
  }
}
```

Works without a key. An API key from Firecrawl raises the limits: send it as `Authorization: Bearer <YOUR_API_KEY>`.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=firecrawl&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.firecrawl.dev%2Fv2%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"firecrawl","type":"http","url":"https://mcp.firecrawl.dev/v2/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "firecrawl": {
      "type": "http",
      "url": "https://mcp.firecrawl.dev/v2/mcp"
    }
  }
}
```

Works without a key. An API key from Firecrawl raises the limits: send it as `Authorization: Bearer <YOUR_API_KEY>`.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "firecrawl": {
      "serverUrl": "https://mcp.firecrawl.dev/v2/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. Works without a key. An API key from Firecrawl raises the limits: send it as `Authorization: Bearer <YOUR_API_KEY>`.

### Codex

```bash
codex mcp add firecrawl --url https://mcp.firecrawl.dev/v2/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.firecrawl]
url = "https://mcp.firecrawl.dev/v2/mcp"
```

Works without a key. An API key from Firecrawl raises the limits: send it as `Authorization: Bearer <YOUR_API_KEY>`.

### Gemini CLI

```bash
gemini mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp
```

Then, inside Gemini CLI, run `/mcp auth firecrawl` to sign in (optional).

This adds it to the current project. Add `-s user` to use it everywhere. Works without a key. An API key from Firecrawl raises the limits: send it as `Authorization: Bearer <YOUR_API_KEY>`.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "firecrawl": {
      "type": "http",
      "url": "https://mcp.firecrawl.dev/v2/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.firecrawl.dev/v2/mcp`.

Works without a key. An API key from Firecrawl raises the limits: send it as `Authorization: Bearer <YOUR_API_KEY>`.

## Details

- Server version: 3.27.3
- MCP protocol version: 2025-11-25
- Last checked: 2026-10-03 (reachable)
- Listed: 2026-10-03
- Updated: 2026-10-03

---
Source: https://mcp.tc/i/firecrawl (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report