Serper Search and Scrape MCP Server

Instructions

Implementation Reference

• src/tools/search-tool.ts:46-53 (handler)

  The scrape method in SerperSearchTools class is the primary handler that executes the scrape tool logic, delegating to the SerperClient and handling errors.

  async scrape(params: IScrapeParams): Promise<IScrapeResult> {
    try {
      const result = await this.serperClient.scrape(params);
      return result;
    } catch (error) {
      throw new Error(`SearchTool: failed to scrape. ${error}`);
    }
  }

• src/index.ts:239-252 (handler)

  The MCP tool call handler for 'scrape' - extracts URL and includeMarkdown parameters from the request, calls searchTools.scrape(), and returns the JSON result.

  case "scrape": {
    const url = request.params.arguments?.url as string;
    const includeMarkdown = request.params.arguments
      ?.includeMarkdown as boolean;
    const result = await searchTools.scrape({ url, includeMarkdown });
    return {
      content: [
        {
          type: "text",
          text: JSON.stringify(result, null, 2),
        },
      ],
    };
  }

• src/index.ts:143-162 (registration)

  Registration of the 'scrape' tool with its name, description, and inputSchema defining url (required) and includeMarkdown (optional boolean) parameters.

  {
    name: "scrape",
    description:
      "Tool to scrape a webpage and retrieve the text and, optionally, the markdown content. It will retrieve also the JSON-LD metadata and the head metadata.",
    inputSchema: {
      type: "object",
      properties: {
        url: {
          type: "string",
          description: "The URL of the webpage to scrape.",
        },
        includeMarkdown: {
          type: "boolean",
          description: "Whether to include markdown content.",
          default: false,
        },
      },
      required: ["url"],
    },
  },

• src/types/serper.ts:50-55 (schema)

  IScrapeParams interface defines the input schema with url (string) and optional includeMarkdown (boolean) for the scrape tool.

   * Scrape parameters for Serper API.
   */
  export interface IScrapeParams {
    url: string;
    includeMarkdown?: boolean;
  }

• src/types/serper.ts:122-130 (schema)

  IScrapeResult interface defines the output schema with text, optional markdown, metadata, jsonld, and credits fields returned by the scrape operation.

   * Represents the result of a scrape operation from the Serper API.
   */
  export interface IScrapeResult {
    text: string;
    markdown?: string;
    metadata?: Record<string, string>;
    jsonld?: Record<string, any>;
    credits?: number;
  }