read_webpage

Instructions

Implementation Reference

• src/index.ts:206-254 (handler)

  The handler logic for the 'read_webpage' tool. Validates arguments, fetches the URL via axios, parses HTML with cheerio, removes script/style elements, extracts title and body text, and returns the content as JSON.

  } else if (request.params.name === 'read_webpage') {
    if (!isValidWebpageArgs(request.params.arguments)) {
      throw new McpError(
        ErrorCode.InvalidParams,
        'Invalid webpage arguments'
      );
    }
  
    const { url } = request.params.arguments;
  
    try {
      const proxyConfig = createProxyConfig();
      const response = await axios.get(url, {
        proxy: proxyConfig,
      });
      const $ = cheerio.load(response.data);
  
      // Remove script and style elements
      $('script, style').remove();
  
      const content: WebpageContent = {
        title: $('title').text().trim(),
        text: $('body').text().trim().replace(/\s+/g, ' '),
        url: url,
      };
  
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify(content, null, 2),
          },
        ],
      };
    } catch (error) {
      if (axios.isAxiosError(error)) {
        return {
          content: [
            {
              type: 'text',
              text: `Webpage fetch error: ${error.message}`,
            },
          ],
          isError: true,
        };
      }
      throw error;
    }
  }

• src/index.ts:73-78 (schema)

  Input validation function (isValidWebpageArgs) that checks that arguments are an object with a string 'url' property.

  const isValidWebpageArgs = (
    args: any
  ): args is { url: string } =>
    typeof args === 'object' &&
    args !== null &&
    typeof args.url === 'string';

• src/index.ts:140-153 (schema)

  Tool registration with name 'read_webpage', description, and input JSON schema defining the required 'url' string parameter.

  {
    name: 'read_webpage',
    description: 'Fetch and extract text content from a webpage',
    inputSchema: {
      type: 'object',
      properties: {
        url: {
          type: 'string',
          description: 'URL of the webpage to read',
        },
      },
      required: ['url'],
    },
  },

• src/index.ts:140-155 (registration)

  Registration of the 'read_webpage' tool in the ListToolsRequestSchema handler, listing it as an available tool.

      {
        name: 'read_webpage',
        description: 'Fetch and extract text content from a webpage',
        inputSchema: {
          type: 'object',
          properties: {
            url: {
              type: 'string',
              description: 'URL of the webpage to read',
            },
          },
          required: ['url'],
        },
      },
    ],
  }));

• src/index.ts:59-63 (helper)

  The WebpageContent interface used to type the returned webpage data (title, text, url).

  interface WebpageContent {
    title: string;
    text: string;
    url: string;
  }