---
title: "Firecrawl: setup for Claude, Cursor, Codex · DotsAgent"
description: "Scrape, crawl, search and extract structured data from websites as Markdown or JSON. Set up Firecrawl in 13 MCP clients."
url: https://dotsagent.io/mcp/servers/firecrawl
---

Search and docs · Firecrawl

# Set up Firecrawl

Scrape, crawl, search and extract structured data from websites as Markdown or JSON.

- **Publisher**: Firecrawl Official
- **Hosted endpoint**: `https://mcp.firecrawl.dev/v2/mcp`
- **Run locally**: `npx -y firecrawl-mcp`
- **Transports**: streamable-http, stdio
- **Authentication**: An API key as bearer token, a keyless tier, or OAuth at /v2/mcp-oauth.
- **Environment**: `FIRECRAWL_API_KEY`
- **What it can touch**: Read-only web retrieval.
- **Licence**: MIT
- **Source**: [github.com/firecrawl/firecrawl-mcp-server](https://github.com/firecrawl/firecrawl-mcp-server)
- **Status**: Active

## Install

The vendor hosts this server, so you only add its URL and nothing runs on your machine. If it needs authentication, the row above says how; OAuth servers prompt you on first connection.

### Claude Code

`shell`

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

### Cursor

`.cursor/mcp.json`

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

### Codex

`~/.codex/config.toml`

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

### Run it locally instead (Cursor)

`.cursor/mcp.json`

```
{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "${env:FIRECRAWL_API_KEY}"
      }
    }
  }
}
```

[Config for other clients →](https://dotsagent.io/mcp/config#add=firecrawl)

## Other servers in search and docs

- [Fetch](https://dotsagent.io/mcp/servers/fetch): Fetches a web page and converts it to Markdown so the model can read it. Part of the MCP project's reference set.

- [AWS Knowledge](https://dotsagent.io/mcp/servers/aws-knowledge): AWS-hosted search over AWS documentation, blog posts, What's New entries and regional availability.

- [Microsoft Learn](https://dotsagent.io/mcp/servers/microsoft-learn): Search and fetch official Microsoft and Azure documentation and code samples.

- [Brave Search](https://dotsagent.io/mcp/servers/brave-search): Brave's own server for web, news, image, video and local search through the Brave Search API.

- [Exa](https://dotsagent.io/mcp/servers/exa): Neural web search, page contents and code-context search for agents, hosted by Exa or run locally with an API key.

- [Tavily](https://dotsagent.io/mcp/servers/tavily): Search, extract, crawl and map websites through Tavily's agent-oriented search API, hosted or run locally.

## Sources

1. [github.com](https://github.com/firecrawl/firecrawl-mcp-server)/firecrawl/firecrawl-mcp-server

Independent reference for people who build AI agents. Not affiliated with any vendor named here.

© 2026 DotsAgent · Facts checked October 1, 2026