SDK INTEGRATION

Web scraping for Mastra

TypeScript-first AI framework with webclaw as a tool provider.

Mastra is a TypeScript framework for building AI applications with agents, workflows, and RAG. webclaw integrates as a tool that Mastra agents can call, providing web extraction with bot bypass and LLM-optimized output.

Setup

Mastra TypeScript — tool definition

import { createTool } from "@mastra/core";
import { Webclaw } from "@webclaw/sdk";
import { z } from "zod";

const wc = new Webclaw({ apiKey: process.env.WEBCLAW_API_KEY! });

export const scrapeWebTool = createTool({
  id: "scrape-web",
  description: "Scrape any URL and return clean markdown content",
  inputSchema: z.object({
    url: z.string().url(),
  }),
  execute: async ({ context }) => {
    const result = await wc.scrape({
      url: context.url,
      formats: ["markdown"],
    });
    return { markdown: result.markdown };
  },
});

Why webclaw for Mastra

  • TypeScript SDK with full type safety
  • Fits Mastra's createTool pattern
  • Fast enough for interactive workflow steps
  • Bot bypass for production scraping

Common use cases

  • Mastra agent workflows with web access
  • TypeScript RAG pipelines
  • Multi-step research workflows
  • Real-time data fetching for LLM apps

Frequently asked questions

How do I register webclaw as a Mastra tool?

Use createTool from @mastra/core and wrap a webclaw SDK call inside the execute function. Register the tool with your Mastra agent or workflow step.

Does webclaw work with Mastra workflows?

Yes. Include the webclaw tool in any workflow step that needs web data. The TypeScript SDK returns typed results that integrate cleanly with Mastra's Zod schemas.

Ready to connect?

Start extracting.

7-day Starter trial. Cancel anytime. Deploy in under a minute or self-host forever. Open source.