firecrawl-mcp-server
installs/mo · npmstarsforks
How to install firecrawl-mcp-server?
firecrawl/firecrawl-mcp-server
$git clone https://github.com/firecrawl/firecrawl-mcp-serverA Model Context Protocol (MCP) server that brings Firecrawl to MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context.
README.md
| 1 | <div align="center"> |
| 2 | <a name="readme-top"></a> |
| 3 | <img |
| 4 | src="https://raw.githubusercontent.com/firecrawl/firecrawl-mcp-server/main/img/fire.png" |
| 5 | height="140" |
| 6 | > |
| 7 | </div> |
| 8 | |
| 9 | # Firecrawl MCP Server |
| 10 | |
| 11 | A Model Context Protocol (MCP) server that brings [Firecrawl](https://github.com/firecrawl/firecrawl) to MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context. |
| 12 | |
| 13 | > Big thanks to [@vrknetha](https://github.com/vrknetha), [@knacklabs](https://www.knacklabs.ai) for the initial implementation! |
| 14 | |
| 15 | ## Features |
| 16 | |
| 17 | - Search the web and get full page content |
| 18 | - Scrape any URL into clean, structured data |
| 19 | - Interact with pages — click, navigate, and operate |
| 20 | - Deep research with autonomous agent |
| 21 | - Automatic retries and rate limiting |
| 22 | - Cloud and self-hosted support |
| 23 | - SSE support |
| 24 | |
| 25 | > Play around with [our MCP Server on MCP.so's playground](https://mcp.so/playground?server=firecrawl-mcp-server) or on [Klavis AI](https://www.klavis.ai/mcp-servers). |
| 26 | |
| 27 | ## Installation |
| 28 | |
| 29 | ### Hosted MCP (keyless free tier) |
| 30 | |
| 31 | Connect to the remote hosted server with no setup: |
| 32 | |
| 33 | ``` |
| 34 | https://mcp.firecrawl.dev/v2/mcp |
| 35 | ``` |
| 36 | |
| 37 | On the keyless free tier, `scrape`, `search`, and `interact` work without an API key (rate-limited). Other tools such as `crawl`, `map`, `agent`, and `extract` still need a key. |
| 38 | |
| 39 | Prefer an API key or OAuth whenever the human can sign up. It unlocks the full tool set and higher limits. With a key, use: |
| 40 | |
| 41 | ``` |
| 42 | https://mcp.firecrawl.dev/{FIRECRAWL_API_KEY}/v2/mcp |
| 43 | ``` |
| 44 | |
| 45 | See the [MCP server docs](https://docs.firecrawl.dev/mcp-server) and the [agent onboarding guide](https://www.firecrawl.dev/agent-onboarding/SKILL.md) for setup details. |
| 46 | |
| 47 | #### Search-only endpoint |
| 48 | |
| 49 | A read-only, search-only surface is also hosted at: |
| 50 | |
| 51 | ``` |
| 52 | https://mcp.firecrawl.dev/v2/mcp-search |
| 53 | ``` |
| 54 | |
| 55 | It exposes a fixed set of six read-only tools: `firecrawl_search` and the five `firecrawl_research_*` tools. It performs no page-content fetching and has its own OAuth identity; the full endpoint above is unchanged. See [docs/search-profile.md](docs/search-profile.md) for the full contract. |
| 56 | |
| 57 | ### Running with npx |
| 58 | |
| 59 | ```bash |
| 60 | env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp |
| 61 | ``` |
| 62 | |
| 63 | ### Manual Installation |
| 64 | |
| 65 | ```bash |
| 66 | npm install -g firecrawl-mcp |
| 67 | ``` |
| 68 | |
| 69 | ### Running on Cursor |
| 70 | |
| 71 | Configuring Cursor 🖥️ |
| 72 | Note: Requires Cursor version 0.45.6+ |
| 73 | For the most up-to-date configuration instructions, please refer to the official Cursor documentation on configuring MCP servers: |
| 74 | [Cursor MCP Server Configuration Guide](https://docs.cursor.com/context/model-context-protocol#configuring-mcp-servers) |
| 75 | |
| 76 | To configure Firecrawl MCP in Cursor **v0.48.6** |
| 77 | |
| 78 | 1. Open Cursor Settings |
| 79 | 2. Go to Features > MCP Servers |
| 80 | 3. Click "+ Add new global MCP server" |
| 81 | 4. Enter the following code: |
| 82 | ```json |
| 83 | { |
| 84 | "mcpServers": { |
| 85 | "firecrawl-mcp": { |
| 86 | "command": "npx", |
| 87 | "args": ["-y", "firecrawl-mcp"], |
| 88 | "env": { |
| 89 | "FIRECRAWL_API_KEY": "YOUR-API-KEY" |
| 90 | } |
| 91 | } |
| 92 | } |
| 93 | } |
| 94 | ``` |
| 95 | |
| 96 | To configure Firecrawl MCP in Cursor **v0.45.6** |
| 97 | |
| 98 | 1. Open Cursor Settings |
| 99 | 2. Go to Features > MCP Servers |
| 100 | 3. Click "+ Add New MCP Server" |
| 101 | 4. Enter the following: |
| 102 | - Name: "firecrawl-mcp" (or your preferred name) |
| 103 | - Type: "command" |
| 104 | - Command: `env FIRECRAWL_API_KEY=your-api-key npx -y firecrawl-mcp` |
| 105 | |
| 106 | > If you are using Windows and are running into issues, try `cmd /c "set FIRECRAWL_API_KEY=your-api-key && npx -y firecrawl-mcp"` |
| 107 | |
| 108 | Replace `your-api-key` with your Firecrawl API key. If you don't have one yet, you can create an account and get it from https://www.firecrawl.dev/app/api-keys |
| 109 | |
| 110 | After adding, refresh the MCP server list to see the new tools. The Composer Agent will automatically use Firecrawl MCP when appropriate, but you can explicitly request it by describing your web scraping needs. Access the Composer via Command+L (Mac), select "Agent" next to the submit button, and enter your query. |
| 111 | |
| 112 | ### Running on Windsurf |
| 113 | |
| 114 | Add this to your `./codeium/windsurf/model_config.json` |
People who liked this also viewed
6 picksType
- ddgsA metasearch library that aggregates results from diverse web search servicesMCP ServersMay 2026
- fliGoogle Flights MCP, CLI and Python LibraryMCP ServersJul 2026
- sembleFast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+readMCP ServersJul 2026
- duckduckgo-mcp-serverA Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.MCP ServersJul 2026
- wikipedia-mcpA Model Context Protocol (MCP) server that retrieves information from Wikipedia to provide context to LLMs.MCP ServersMay 2026
- arxiv-mcp-serverA Model Context Protocol server for searching and analyzing arXiv papersMCP ServersJul 2026
