Firecrawl MCP Server for Vercel AI SDKGive Vercel AI SDK instant access to 6 tools to Cancel Active Crawl, Get Api Usage, Get Crawl Status, and more
The Vercel AI SDK is the TypeScript toolkit for building AI-powered applications. Connect Firecrawl through Vinkius and every tool is available as a typed function. ready for React Server Components, API routes, or any Node.js backend.
Ask AI about this App Connector for Vercel AI SDK
The Firecrawl app connector for Vercel AI SDK is a standout in the Friends Mcp category — giving your AI agent 6 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
import { createMCPClient } from "@ai-sdk/mcp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
async function main() {
const mcpClient = await createMCPClient({
transport: {
type: "http",
// Your Vinkius token. get it at cloud.vinkius.com
url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
},
});
try {
const tools = await mcpClient.tools();
const { text } = await generateText({
model: openai("gpt-4o"),
tools,
prompt: "Using Firecrawl, list all available capabilities.",
});
console.log(text);
} finally {
await mcpClient.close();
}
}
main();
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Firecrawl MCP Server
Connect your Firecrawl account to any AI agent and take full control of your web data acquisition and recursive crawling workflows through natural conversation.
The Vercel AI SDK gives every Firecrawl tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 6 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
What you can do
- Web Scrape Orchestration — Scrape any single URL programmatically into high-fidelity Markdown, excluding boilerplate content like headers and footers automatically
- Recursive Crawling — Programmatically discover and scrape all subpages starting from a root URL to build comprehensive knowledge bases and RAG pipelines
- Site Mapping — Quickly identify all reachable links on a domain without full content extraction to understand website structures and hierarchies
- Visual Capture — Capture full-page screenshots of any URL directly through your agent to maintain a visual record of web data
- Usage Monitoring — Track your Firecrawl credit usage, remaining limits, and active crawl job statuses in real-time
The Firecrawl MCP Server exposes 6 tools through the Vinkius. Connect it to Vercel AI SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
All 6 Firecrawl tools available for Vercel AI SDK
When Vercel AI SDK connects to Firecrawl through Vinkius, your AI agent gets direct access to every tool listed below — spanning data-extraction, markdown-conversion, rag-pipelines, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
Stop an ongoing crawl
Check Firecrawl credit usage
Check the status of a crawl job
Discover all URLs on a site
Turn a single URL into clean Markdown
Returns a job ID. Recursively crawl a website
Connect Firecrawl to Vercel AI SDK via MCP
Follow these steps to wire Firecrawl into Vercel AI SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install dependencies
npm install @ai-sdk/mcp ai @ai-sdk/openaiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the script
agent.ts and run with npx tsx agent.tsExplore tools
Why Use Vercel AI SDK with the Firecrawl MCP Server
Vercel AI SDK provides unique advantages when paired with Firecrawl through the Model Context Protocol.
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same Firecrawl integration everywhere
Built-in streaming UI primitives let you display Firecrawl tool results progressively in React, Svelte, or Vue components
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
Firecrawl + Vercel AI SDK Use Cases
Practical scenarios where Vercel AI SDK combined with the Firecrawl MCP Server delivers measurable value.
AI-powered web apps: build dashboards that query Firecrawl in real-time and stream results to the UI with zero loading states
API backends: create serverless endpoints that orchestrate Firecrawl tools and return structured JSON responses to any frontend
Chatbots with tool use: embed Firecrawl capabilities into conversational interfaces with streaming responses and tool call visibility
Internal tools: build admin panels where team members interact with Firecrawl through natural language queries
Example Prompts for Firecrawl in Vercel AI SDK
Ready-to-use prompts you can give your Vercel AI SDK agent to start working with Firecrawl immediately.
"Turn 'https://stripe.com/docs/api' into clean Markdown."
"Crawl 'https://docs.firecrawl.dev' recursively with a limit of 10 pages."
"Map all internal links for 'https://github.com/vinkius'."
Troubleshooting Firecrawl MCP Server with Vercel AI SDK
Common issues when connecting Firecrawl to Vercel AI SDK through the Vinkius, and how to resolve them.
createMCPClient is not a function
npm install @ai-sdk/mcpFirecrawl + Vercel AI SDK FAQ
Common questions about integrating Firecrawl MCP Server with Vercel AI SDK.
How does the Vercel AI SDK connect to MCP servers?
createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.Can I use MCP tools in Edge Functions?
Does it support streaming tool results?
useChat and streamText that handle tool calls and display results progressively in the UI.