OneSearch MCP Server

/** * The following tools are based on the Firecrawl MCP Server * https://github.com/mendableai/firecrawl-mcp-server */ import { Tool } from '@modelcontextprotocol/sdk/types.js'; // tools definition export const SEARCH_TOOL: Tool = { name: 'one_search', description: 'Search and retrieve content from web pages. ' + 'Returns SERP results by default (url, title, description).', inputSchema: { type: 'object', properties: { query: { type: 'string', description: 'Search query string', }, limit: { type: 'number', description: 'Maximum number of results to return (default: 10)', }, language: { type: 'string', description: 'Language code for search results (default: auto)', }, categories: { type: 'string', enum: [ 'general', 'news', 'images', 'videos', 'it', 'science', 'map', 'music', 'files', 'social_media', ], description: 'Categories to search for (default: general)', }, timeRange: { type: 'string', description: 'Time range for search results (default: all)', enum: [ 'all', 'day', 'week', 'month', 'year', ], }, }, required: ['query'], }, }; export const MAP_TOOL: Tool = { name: 'one_map', description: 'Discover URLs from a starting point. Can use both sitemap.xml and HTML link discovery.', inputSchema: { type: 'object', properties: { url: { type: 'string', description: 'Starting URL for URL discovery', }, search: { type: 'string', description: 'Optional search term to filter URLs', }, ignoreSitemap: { type: 'boolean', description: 'Skip sitemap.xml discovery and only use HTML links', }, sitemapOnly: { type: 'boolean', description: 'Only use sitemap.xml for discovery, ignore HTML links', }, includeSubdomains: { type: 'boolean', description: 'Include URLs from subdomains in results', }, limit: { type: 'number', description: 'Maximum number of URLs to return', }, }, required: ['url'], }, }; export const SCRAPE_TOOL: Tool = { name: 'one_scrape', description: 'Scrape a single webpage with advanced options for content extraction. ' + 'Supports various formats including markdown, HTML, and screenshots. ' + 'Can execute custom actions like clicking or scrolling before scraping.', inputSchema: { type: 'object', properties: { url: { type: 'string', description: 'The URL to scrape', }, formats: { type: 'array', items: { type: 'string', enum: [ 'markdown', 'html', 'rawHtml', 'screenshot', 'links', 'screenshot@fullPage', 'extract', ], }, description: "Content formats to extract (default: ['markdown'])", }, onlyMainContent: { type: 'boolean', description: 'Extract only the main content, filtering out navigation, footers, etc.', }, includeTags: { type: 'array', items: { type: 'string' }, description: 'HTML tags to specifically include in extraction', }, excludeTags: { type: 'array', items: { type: 'string' }, description: 'HTML tags to exclude from extraction', }, waitFor: { type: 'number', description: 'Time in milliseconds to wait for dynamic content to load', }, timeout: { type: 'number', description: 'Maximum time in milliseconds to wait for the page to load', }, actions: { type: 'array', items: { type: 'object', properties: { type: { type: 'string', enum: [ 'wait', 'click', 'screenshot', 'write', 'press', 'scroll', 'scrape', 'executeJavascript', ], description: 'Type of action to perform', }, selector: { type: 'string', description: 'CSS selector for the target element', }, milliseconds: { type: 'number', description: 'Time to wait in milliseconds (for wait action)', }, text: { type: 'string', description: 'Text to write (for write action)', }, key: { type: 'string', description: 'Key to press (for press action)', }, direction: { type: 'string', enum: ['up', 'down'], description: 'Scroll direction', }, script: { type: 'string', description: 'JavaScript code to execute', }, fullPage: { type: 'boolean', description: 'Take full page screenshot', }, }, required: ['type'], }, description: 'List of actions to perform before scraping', }, extract: { type: 'object', properties: { schema: { type: 'object', description: 'Schema for structured data extraction', }, systemPrompt: { type: 'string', description: 'System prompt for LLM extraction', }, prompt: { type: 'string', description: 'User prompt for LLM extraction', }, }, description: 'Configuration for structured data extraction', }, mobile: { type: 'boolean', description: 'Use mobile viewport', }, skipTlsVerification: { type: 'boolean', description: 'Skip TLS certificate verification', }, removeBase64Images: { type: 'boolean', description: 'Remove base64 encoded images from output', }, location: { type: 'object', properties: { country: { type: 'string', description: 'Country code for geolocation', }, languages: { type: 'array', items: { type: 'string' }, description: 'Language codes for content', }, }, description: 'Location settings for scraping', }, }, required: ['url'], }, }; export const EXTRACT_TOOL: Tool = { name: 'one_extract', description: 'Extract structured information from web pages using LLM. ' + 'Supports both cloud AI and self-hosted LLM extraction.', inputSchema: { type: 'object', properties: { urls: { type: 'array', items: { type: 'string' }, description: 'List of URLs to extract information from', }, prompt: { type: 'string', description: 'Prompt for the LLM extraction', }, systemPrompt: { type: 'string', description: 'System prompt for LLM extraction', }, schema: { type: 'object', description: 'JSON schema for structured data extraction', }, allowExternalLinks: { type: 'boolean', description: 'Allow extraction from external links', }, enableWebSearch: { type: 'boolean', description: 'Enable web search for additional context', }, includeSubdomains: { type: 'boolean', description: 'Include subdomains in extraction', }, }, required: ['urls'], }, };