tavily-extract
Extract and process raw web content from URLs for data collection, content analysis, and research tasks using basic or advanced extraction methods.
Instructions
A powerful web content extraction tool that retrieves and processes raw content from specified URLs, ideal for data collection, content analysis, and research tasks.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | List of URLs to extract content from | |
| extract_depth | No | Depth of extraction - 'basic' or 'advanced', if usrls are linkedin use 'advanced' or if explicitly told to use advanced | basic |
| include_images | No | Include a list of images extracted from the urls in the response |
Implementation Reference
- src/index.ts:478-493 (handler)Core handler function that executes the tavily-extract tool by sending a POST request to the Tavily extract API with the provided parameters.
async extract(params: any): Promise<TavilyResponse> { try { const response = await this.axiosInstance.post(this.baseURLs.extract, { ...params, api_key: API_KEY }); return response.data; } catch (error: any) { if (error.response?.status === 401) { throw new Error('Invalid API key'); } else if (error.response?.status === 429) { throw new Error('Usage limit exceeded'); } throw error; } } - src/index.ts:190-215 (schema)Defines the input schema, description, and name for the tavily-extract tool, used in tool listing and validation.
{ name: "tavily-extract", description: "A powerful web content extraction tool that retrieves and processes raw content from specified URLs, ideal for data collection, content analysis, and research tasks.", inputSchema: { type: "object", properties: { urls: { type: "array", items: { type: "string" }, description: "List of URLs to extract content from" }, extract_depth: { type: "string", enum: ["basic","advanced"], description: "Depth of extraction - 'basic' or 'advanced', if usrls are linkedin use 'advanced' or if explicitly told to use advanced", default: "basic" }, include_images: { type: "boolean", description: "Include a list of images extracted from the urls in the response", default: false, } }, required: ["urls"] } }, - src/index.ts:372-378 (handler)Dispatcher case in the CallToolRequest handler that invokes the extract method for tavily-extract tool calls.
case "tavily-extract": response = await this.extract({ urls: args.urls, extract_depth: args.extract_depth, include_images: args.include_images }); break; - src/index.ts:530-566 (helper)Helper function to format the Tavily API response (used by tavily-extract and search) into a readable text output for the tool response.
function formatResults(response: TavilyResponse): string { // Format API response into human-readable text const output: string[] = []; // Include answer if available if (response.answer) { output.push(`Answer: ${response.answer}`); } // Format detailed search results output.push('Detailed Results:'); response.results.forEach(result => { output.push(`\nTitle: ${result.title}`); output.push(`URL: ${result.url}`); output.push(`Content: ${result.content}`); if (result.raw_content) { output.push(`Raw Content: ${result.raw_content}`); } }); // Add images section if available if (response.images && response.images.length > 0) { output.push('\nImages:'); response.images.forEach((image, index) => { if (typeof image === 'string') { output.push(`\n[${index + 1}] URL: ${image}`); } else { output.push(`\n[${index + 1}] URL: ${image.url}`); if (image.description) { output.push(` Description: ${image.description}`); } } }); } return output.join('\n'); } - src/index.ts:109-215 (registration)Registers tavily-extract in the list of available tools returned by ListToolsRequest.
// Define available tools: tavily-search and tavily-extract const tools: Tool[] = [ { name: "tavily-search", description: "A powerful web search tool that provides comprehensive, real-time results using Tavily's AI search engine. Returns relevant web content with customizable parameters for result count, content type, and domain filtering. Ideal for gathering current information, news, and detailed web content analysis.", inputSchema: { type: "object", properties: { query: { type: "string", description: "Search query" }, search_depth: { type: "string", enum: ["basic","advanced"], description: "The depth of the search. It can be 'basic' or 'advanced'", default: "basic" }, topic : { type: "string", enum: ["general","news"], description: "The category of the search. This will determine which of our agents will be used for the search", default: "general" }, days: { type: "number", description: "The number of days back from the current date to include in the search results. This specifies the time frame of data to be retrieved. Please note that this feature is only available when using the 'news' search topic", default: 3 }, time_range: { type: "string", description: "The time range back from the current date to include in the search results. This feature is available for both 'general' and 'news' search topics", enum: ["day", "week", "month", "year", "d", "w", "m", "y"], }, max_results: { type: "number", description: "The maximum number of search results to return", default: 10, minimum: 5, maximum: 20 }, include_images: { type: "boolean", description: "Include a list of query-related images in the response", default: false, }, include_image_descriptions: { type: "boolean", description: "Include a list of query-related images and their descriptions in the response", default: false, }, /* // Since the mcp server is using AI clients to generate answers form the search results, we don't need to include this feature. include_answer: { type: ["boolean", "string"], enum: [true, false, "basic", "advanced"], description: "Include an answer to original query, generated by an LLM based on Tavily's search results. Can be boolean or string ('basic'/'advanced'). 'basic'/true answer will be quick but less detailed, 'advanced' answer will be more detailed but take longer to generate", default: false, }, */ include_raw_content: { type: "boolean", description: "Include the cleaned and parsed HTML content of each search result", default: false, }, include_domains: { type: "array", items: { type: "string" }, description: "A list of domains to specifically include in the search results, if the user asks to search on specific sites set this to the domain of the site", default: [] }, exclude_domains: { type: "array", items: { type: "string" }, description: "List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site", default: [] } }, required: ["query"] } }, { name: "tavily-extract", description: "A powerful web content extraction tool that retrieves and processes raw content from specified URLs, ideal for data collection, content analysis, and research tasks.", inputSchema: { type: "object", properties: { urls: { type: "array", items: { type: "string" }, description: "List of URLs to extract content from" }, extract_depth: { type: "string", enum: ["basic","advanced"], description: "Depth of extraction - 'basic' or 'advanced', if usrls are linkedin use 'advanced' or if explicitly told to use advanced", default: "basic" }, include_images: { type: "boolean", description: "Include a list of images extracted from the urls in the response", default: false, } }, required: ["urls"] } },