How to Use the Firecrawl MCP in Cursor

Q: How do I add the Firecrawl MCP server to my Cursor project?

Create a .cursor/mcp.json file in your project root and define the server. Once saved, Cursor automatically starts the server and exposes the scraping tools to your agent.

Q: Can Cursor use Firecrawl to read documentation behind login screens?

No, the scrapepage tool only accesses publicly available web pages. If the documentation requires authentication, the server will return an authorization error to Cursor.

Q: Is the crawlsite tool running locally inside my editor?

No, crawlsite executes on the remote Firecrawl infrastructure to avoid consuming your local CPU. Your editor receives a job ID to monitor the progress while you continue writing code.

Feed live web documentation directly into Cursor to write code with real API responses instead of outdated stubs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firecrawl MCP to Cursor

Create your Vinkius account to connect Firecrawl to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Firecrawl with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Cursor code using live scraped documentation

`scrape_page` pulls clean Markdown from API docs directly into your active Cursor editing session. This allows your agent to reference live, up-to-date syntax instead of relying on training data from two years ago. You ask the editor to implement a new SDK, and the tool fetches the exact page you need. Your agent then writes functional code based on the actual DOM content it just parsed.

Query the web to resolve compiler errors in Cursor

`search_web` runs a search query and returns scraped Markdown from the top search results directly to your editor. The MCP server runs a search query when a weird build error pops up, allowing your agent to check the web for recent GitHub issues or StackOverflow threads. Instead of switching to a browser tab, you let Cursor pull the fix directly. The tool extracts the relevant code blocks from the search results so you can apply the patch immediately.

Map entire developer portals before generating code

`map_site` discovers every URL on a target developer portal to give your editor a bird's-eye view of the API structure. Cursor reads this sitemap to locate the exact endpoint documentation required for your task. This prevents your editor from hallucinating endpoint paths or guessing parameter structures. You get precise code generation because the agent knows exactly which URLs to scrape next.

Setup guide

Set up Firecrawl MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Firecrawl MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Firecrawl transactions." If the MCP tools are loaded correctly, Cursor will call the Firecrawl tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "firecrawl-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Firecrawl. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Firecrawl now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Firecrawl MCP in Cursor

Create a `.cursor/mcp.json` file in your project root and define the server. Once saved, Cursor automatically starts the server and exposes the scraping tools to your agent.

No, the `scrape_page` tool only accesses publicly available web pages. If the documentation requires authentication, the server will return an authorization error to Cursor.

The MCP server manages the connection to the scraping API using your configured API token. It handles the underlying requests, but you should monitor your plan limits if Cursor runs recursive site crawls.

No, `crawl_site` executes on the remote Firecrawl infrastructure to avoid consuming your local CPU. Your editor receives a job ID to monitor the progress while you continue writing code.

No, the server only processes the specific target URLs, search queries, and API keys you pass to it. Your local source code in Cursor remains entirely private and never leaves your machine.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript