Skip to main content
Glama
cortex8

DataForSEO MCP Server

by cortex8

on_page_content_parsing

Parse webpage content to extract structured data including links, headings, and text for SEO analysis and content processing.

Instructions

This endpoint allows parsing the content on any page you specify and will return the structured content of the target page, including link URLs, anchors, headings, and textual content.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
accept_languageNoAccept-Language header value
custom_jsNoCustom JavaScript code to execute
custom_user_agentNoCustom User-Agent header
enable_javascriptNoEnable JavaScript rendering
urlYesURL of the page to parse

Implementation Reference

  • The handle() method executes the tool logic: sends POST request to DataForSEO /v3/on_page/content_parsing/live, processes response based on config, and returns formatted markdown content or full response.
    async handle(params: { url: string; enable_javascript?: boolean; custom_js?: string; custom_user_agent?: string; accept_language?: string; }): Promise<any> { try { const response = await this.dataForSEOClient.makeRequest('/v3/on_page/content_parsing/live', 'POST', [{ url: params.url, enable_javascript: params.enable_javascript, custom_js: params.custom_js, custom_user_agent: params.custom_user_agent, accept_language: params.accept_language, markdown_view: true }]); console.error(JSON.stringify(response)); if(defaultGlobalToolConfig.fullResponse || this.supportOnlyFullResponse()){ let data = response as DataForSEOFullResponse; this.validateResponseFull(data); let result = data.tasks[0].result; return this.formatResponse(result); } else{ let data = response as DataForSEOResponse; this.validateResponse(data); let result = data.items[0].page_as_markdown; return this.formatResponse(result); } } catch (error) { return this.formatErrorResponse(error); } }
  • Defines the input schema using Zod for parameters: url (required), and optional flags for JS, custom JS, UA, language.
    getParams(): z.ZodRawShape { return { url: z.string().describe("URL of the page to parse"), enable_javascript: z.boolean().optional().describe("Enable JavaScript rendering"), custom_js: z.string().optional().describe("Custom JavaScript code to execute"), custom_user_agent: z.string().optional().describe("Custom User-Agent header"), accept_language: z.string().optional().describe("Accept-Language header value"), }; }
  • Registers the ContentParsingTool (among others) in the OnPageApiModule's getTools() by instantiating it and mapping to a ToolDefinition object using getName() 'on_page_content_parsing' as key, exposing description, params, and wrapped handler.
    getTools(): Record<string, ToolDefinition> { const tools = [ new ContentParsingTool(this.dataForSEOClient), new InstantPagesTool(this.dataForSEOClient), new LighthouseTool(this.dataForSEOClient), // Add more tools here ]; return tools.reduce((acc, tool) => ({ ...acc, [tool.getName()]: { description: tool.getDescription(), params: tool.getParams(), handler: (params: any) => tool.handle(params), }, }), {}); }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cortex8/oyt-dataforseo-mcp-worker'

If you have feedback or need assistance with the MCP directory API, please join our Discord server