How to Use the Firecrawl MCP in Vercel AI SDK

Q: Can Firecrawl handle dynamic content in Vercel AI SDK apps?

Yes. The scrapepage tool handles JavaScript rendering and cookie banners automatically. Your AI client receives clean text regardless of how the page is built.

Convert any website into clean Markdown for your Vercel AI SDK projects with this MCP Server.

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 Vercel AI SDK

Create your Vinkius account to connect Firecrawl to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live site scraping for Vercel AI SDK

Feed clean Markdown directly into your LLM streams. Use `scrape_page` to bypass anti-bot protections and get content into your UI without the wait. Your users see data materialize in real-time. By connecting this MCP Server, you move from static data to live web context inside your Edge Functions.

Map and crawl site structures

Use `map_site` to fetch every URL on a domain before you commit to a full scrape. This prevents wasted tokens and keeps your context windows focused on high-signal pages. Once you confirm the structure, call `crawl_site` to pull the entire site into your workflow. The server handles the job queue so you can track progress across your frontend state.

Integrated web search

Trigger `search_web` to pull facts from the live web directly into your AI agent. It combines search results with automated extraction, so you get usable text instead of messy HTML. This tool turns your Vercel AI SDK app into a research engine. You get the top results formatted for immediate injection into your prompt chain.

Setup guide

Set up Firecrawl MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Firecrawl tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Firecrawl transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the MCP client package and point it to your Vinkius endpoint. You then pass the tools from this MCP Server directly into your `generateText` or `streamText` calls.

Yes. The `scrape_page` tool handles JavaScript rendering and cookie banners automatically. Your AI client receives clean text regardless of how the page is built.

It works perfectly. Because the MCP Server outputs clean Markdown, your streaming responses stay fast and coherent for the end user.

Vinkius manages your connection. You provide one endpoint token, and the server handles authentication for your requests.

Your scraped data is ephemeral. Firecrawl processes the raw HTML into Markdown and passes it to your agent; we do not store your target site content or search history.

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