puppeteer-vision-mcp-server/build/server/tools.js

MCP Server for scraping webpages and converting to markdown

import { z } from 'zod';
import { visitWebPage } from '../scrapers/webpage-scraper.js';
/**
 * Registers MCP tools with the server
 * @param server The MCP server instance
 */
export function registerTools(server) {
    server.tool("scrape-webpage", "Scrapes a webpage and converts it to markdown format", {
        url: z.string().url().describe("The URL of the webpage to scrape"),
        autoInteract: z.boolean().optional().default(true).describe("Whether to automatically handle interactive elements like cookies, captchas, etc."),
        maxInteractionAttempts: z.number().int().min(0).max(10).optional().default(3).describe("Maximum number of interaction attempts"),
        waitForNetworkIdle: z.boolean().optional().default(true).describe("Whether to wait for network to be idle before processing"),
        includeSameDomainLinks: z.boolean().optional().default(false).describe("Whether to append a list of same-domain links to the markdown output")
    }, async ({ url, autoInteract, maxInteractionAttempts, waitForNetworkIdle, includeSameDomainLinks, }, _extra) => {
        console.log(`Received scrape request for URL: ${url}, autoInteract: ${autoInteract}, maxAttempts: ${maxInteractionAttempts}`);
        try {
            const result = await visitWebPage({
                url,
                autoInteract,
                maxInteractionAttempts,
                waitForNetworkIdle,
                includeSameDomainLinks
            });
            if (result.error) {
                return createErrorResponse(result.error.message);
            }
            // Limit the size of returned content if too large
            const maxLength = 100000; // Set a reasonable limit
            let markdownContent = result.data || "";
            let message = "Scraping successful";
            if (markdownContent.length > maxLength) {
                markdownContent = markdownContent.substring(0, maxLength);
                message = `Content truncated due to size (total size: ${markdownContent.length} characters)`;
            }
            console.log(`Scraping successful. Payload size: ${markdownContent.length} chars.`);
            return createSuccessResponse(markdownContent, message);
        }
        catch (error) {
            console.error("Error processing 'scrape-webpage' tool:", error);
            return createErrorResponse(`Error scraping webpage: ${error.message}`);
        }
    });
}
/**
 * Creates a success response for the MCP tool
 * @param text The markdown text content
 * @param message An optional message to include
 * @returns The formatted tool response
 */
function createSuccessResponse(text, message = "Scraping successful") {
    return {
        content: [{ type: "text", text }],
        _meta: {
            message,
            success: true,
            contentSize: text.length
        },
        isError: false
    };
}
/**
 * Creates an error response for the MCP tool
 * @param message The error message
 * @returns The formatted tool response
 */
function createErrorResponse(message) {
    return {
        content: [{ type: "text", text: "" }],
        _meta: {
            message: message,
            success: false
        },
        isError: true
    };
}