Firecrawl

A Model Context Protocol (MCP) server that bringsFirecrawlto MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context.

Big thanks to@vrknetha,@knacklabsfor the initial implementation!

Play around withour MCP Server on MCP.so's playgroundor onKlavis AI.

Authorization: Bearer <FIRECRAWL_API_KEY>

Never put an API key in the server URL. Never put an API key in an agent chat. Configure it directly in the client or secret manager. See thehosted MCP setup guideand theagent onboarding guidefor client-specific instructions.

It exposes a fixed set of six read-only tools:firecrawl_searchand the fivefirecrawl_research_*tools. It performs no page-content fetching and has its own OAuth identity; the full endpoint above is unchanged. Seedocs/search-profile.mdfor the full contract.

env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp

Configuring Cursor 🖥️ Note: Requires Cursor version 0.45.6+ For the most up-to-date configuration instructions, please refer to the official Cursor documentation on configuring MCP servers:Cursor MCP Server Configuration Guide

{ "mcpServers": { "firecrawl-mcp": { "command": "npx", "args": ["-y", "firecrawl-mcp"], "env": { "FIRECRAWL_API_KEY": "YOUR-API-KEY" } } } }

To configure Firecrawl MCP in Cursorv0.45.6
- Open Cursor Settings
- Go to Features > MCP Servers
- Click "+ Add New MCP Server"
- Enter the following:

- Name: "firecrawl-mcp" (or your preferred name)
- Type: "command"
- Command:env FIRECRAWL_API_KEY=your-api-key npx -y firecrawl-mcp

If you are using Windows and are running into issues, trycmd /c "set FIRECRAWL_API_KEY=your-api-key && npx -y firecrawl-mcp"

Replaceyour-api-keywith your Firecrawl API key. If you don't have one yet, you can create an account and get it fromhttps://www.firecrawl.dev/app/api-keys

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

To run the server using Streamable HTTP locally instead of the default stdio transport:

env HTTP_STREAMABLE_SERVER=true FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp

To install Firecrawl for Claude Desktop automatically viaSmithery:

npx -y @smithery/cli install @mendableai/mcp-server-firecrawl --client claude

{ "mcp": { "inputs": [ { "type": "promptString", "id": "apiKey", "description": "Firecrawl API Key", "password": true } ], "servers": { "firecrawl": { "command": "npx", "args": ["-y", "firecrawl-mcp"], "env": { "FIRECRAWL_API_KEY": "${input:apiKey}" } } } } }

Optionally, you can add it to a file called.vscode/mcp.jsonin your workspace. This will allow you to share the configuration with others:

{ "inputs": [ { "type": "promptString", "id": "apiKey", "description": "Firecrawl API Key", "password": true } ], "servers": { "firecrawl": { "command": "npx", "args": ["-y", "firecrawl-mcp"], "env": { "FIRECRAWL_API_KEY": "${input:apiKey}" } } } }

- FIRECRAWL_API_KEY: Your Firecrawl API key

- Required when using cloud API (default)
- Optional when using self-hosted instance withFIRECRAWL_API_URL

- Example:https://firecrawl.your-domain.com
- If not provided, the cloud API will be used (requires API key)

Hosted Firecrawl can issue OAuthaccess tokens(fco_…) via the authorization server onfirecrawl.dev. This MCP server forwards whichever credential it resolves to the Firecrawl API asAuthorization: Bearer ….

In hosted mode (CLOUD_SERVICE=true) a second in-process instance serves thesearch-only endpoint. The bundled service has a fixed deployment contract: nginx routes/v2/mcp-searchto the instance on local port3001, and the OAuth protected-resource identifier ishttps://mcp.firecrawl.dev/v2/mcp-search.

# Required for self-hosted export FIRECRAWL_API_URL=https://firecrawl.your-domain.com # Optional authentication for self-hosted export FIRECRAWL_API_KEY=your-api-key # If your instance requires auth

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

Use this guide to select the right tool for your task:

- If you know the exact URL you want:usescrape(with JSON format for structured data)
- If you have multiple known URLs:callscrapefor each URL. If you specifically need one bulk API operation, use the Firecrawl API batch endpoint outside MCP.
- If you need to discover URLs on a site:usemap
- If you want to search the web for info:usesearch
- If you have a programming question(a library, an API contract, an error message, a known bug): usedeveloper search
- If you need scientific papers(biomedical, life-science, clinical, or arXiv literature): useresearch tools— they search paper abstracts and full text.searchwithcategories: ["research"]is a different thing: a website filter over ordinary web results.
- If you need complex research across multiple unknown sources:useagent
- If you want to analyze a whole site or section:usecrawl(with limits!)
- If you need interactive browser automation(click, type, navigate): useinteractwith a URL for a fresh page, orscrape+interactwhen you already scraped the page or need tighter scrape control

When usingscrape, choose the right format:

- JSON format (recommended for most cases):Use when you need specific data from a page. Define a schema based on what you need to extract. This keeps responses small and avoids context window overflow.
- Markdown format (use sparingly):Only when you genuinely need the full page content, such as reading an entire article for summarization or analyzing page structure.

Scrape content from a single URL with advanced options.

- Single page content extraction, when you know exactly which page contains the information.

- Extracting content from multiple pages (use repeated scrape calls for known URLs, or map + scrape to discover URLs first, or crawl for full page content)
- When you're unsure which page contains the information (use search)

- Passing a list of URLs to one scrape call. Call scrape once per URL in MCP. If you specifically need one bulk API operation, use the Firecrawl API batch endpoint outside MCP.
- Using markdown format by default (use JSON format to extract only what you need).

- JSON format (preferred):For most use cases, use JSON format with a schema to extract only the specific data needed. This keeps responses focused and prevents context window overflow.
- Markdown format:Only when the task genuinely requires full page content (e.g., summarizing an entire article, analyzing page structure).

"Get the product details fromhttps://example.com/product."

{ "name": "firecrawl_scrape", "arguments": { "url": "https://example.com/product", "formats": [ { "type": "json", "prompt": "Extract the product information", "schema": { "type": "object", "properties": { "name": { "type": "string" }, "price": { "type": "number" }, "description": { "type": "string" } }, "required": ["name", "price"] } } ] } }

Usage Example (markdown format - when full content needed):

{ "name": "firecrawl_scrape", "arguments": { "url": "https://example.com/article", "formats": ["markdown"], "onlyMainContent": true } }

Usage Example (branding format - extract brand identity):

{ "name": "firecrawl_scrape", "arguments": { "url": "https://example.com", "formats": ["branding"] } }

Branding format:Extracts comprehensive brand identity (colors, fonts, typography, spacing, logo, UI components) for design analysis or style replication.Privacy:SetredactPII: trueto return content with personally identifiable information redacted.

- JSON structured data, markdown, branding profile, or other formats as specified.

Map a website to discover all indexed URLs on the site.

- Discovering URLs on a website before deciding what to scrape
- Finding specific sections of a website

- When you already know which specific URL you need (use scrape)
- When you need the content of the pages (use scrape after mapping)

- Using crawl to discover URLs instead of map

"List all URLs on example.com."

{ "name": "firecrawl_map", "arguments": { "url": "https://example.com" } }

Search the web and optionally extract content from search results.

- Finding specific information across multiple websites, when you don't know which website has the information.
- When you need the most relevant content for a query

- When you already know which website to scrape (use scrape)
- When you need comprehensive coverage of a single website (use map or crawl)

- Using crawl or map for open-ended questions (use search instead)

{ "name": "firecrawl_search", "arguments": { "query": "remote work stipend policies at tech companies", "highlights": true, "limit": 5, "lang": "en", "country": "us", "scrapeOptions": { "formats": ["markdown"], "onlyMainContent": true, "redactPII": true } } }

Sethighlightstotrueto request query-relevant highlights orfalseto keep the original search snippets. Omit it to use the API's default behavior.

For scientific papers, seeResearch Tools: they search paper abstracts and full text, whilecategories: ["research"]here filters ordinary web results to research-affiliated websites.

- Array of search results (with optional scraped content), plus anidfield. Pass thatidtofirecrawl_search_feedbackafter you've used the results to refund 1 credit (search costs 2) and improve search quality.

"Compare remote work stipend policies across tech companies."

3b. Search Feedback Tool (firecrawl_search_feedback)