How to Use the Firecrawl MCP in Mastra AI

Q: How do I integrate Firecrawl into my Mastra AI agents?

Add this MCP Server to your MCPClient configuration. Once connected, spread the tools into your agent definition and they become available for your workflows.

Q: Can I add human approval to Firecrawl tools in Mastra AI?

Yes. Use Mastra's requireToolApproval setting on the MCP tools. This ensures a human reviews the crawl target before the agent executes the scrape.

Build resilient web-scraping workflows in Mastra AI with the Firecrawl 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 Mastra AI

Create your Vinkius account to connect Firecrawl to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated site scraping for Mastra AI

Trigger `scrape_page` within your Mastra workflows to get clean text from any URL. It strips away the noise so your agents only process the data that matters. Because this runs as an MCP Server, you can chain these calls into your existing logic. If a scrape fails, your workflow engine handles the retry logic automatically.

Recursive crawling for complex agents

Deploy `crawl_site` to index entire domains for your Mastra agents. You get a job ID back, allowing your workflow to pause and wait for the data to be ready. Use this to build knowledge bases that update themselves. Your agents can trigger these crawls based on events, keeping your internal data fresh.

Site mapping for workflow logic

Use `map_site` to determine which URLs your agent should visit next. This is critical for agents that need to navigate documentation or product catalogs systematically. By understanding the structure first, you reduce the number of calls your agent makes. It saves time and keeps your workflow execution costs low.

Setup guide

Set up Firecrawl MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Firecrawl tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "firecrawl-mcp-client",
  servers: {
    "firecrawl-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Firecrawl Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Firecrawl tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Firecrawl transactions"
);
console.log(result.text);

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 Mastra AI

Add this MCP Server to your `MCPClient` configuration. Once connected, spread the tools into your agent definition and they become available for your workflows.

Yes. Use Mastra's `requireToolApproval` setting on the MCP tools. This ensures a human reviews the crawl target before the agent executes the scrape.

Mastra handles the retries. When you define your workflow, you can set the retry policy for any tool call made to this MCP Server.

The server manages anti-bot bypass for you. If a request is blocked, it returns an error that your Mastra workflow can catch and handle via conditional branching.

We use a zero-trust architecture. All scraped content, such as raw text and site metadata, is processed in an ephemeral sandbox and is never persisted on our end.

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