chunks_per_source
(number, optional, default: 3): For searchdepth: "advanced", the number of content chunks to retrieve from each source (1-3).
How to use it
chunks_per_source is exposed by the Deep Research MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the chunks_per_source tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Deep Research MCP
npx -y @smithery/cli install @pinkpixel/dev-deep-research-mcp --client claudeOther tools in Deep Research MCP (28)
(boolean, optional, default: false): Whether to allow the crawler to follow links to external domains.
(array of strings, optional, default: []): Filter URLs for crawling using predefined categories (e.g., "Blog", "Documentation", "Careers"). Refer to Tavily Crawl API for all options.
(array of strings, optional, default: []): Regex patterns to exclude specific domains or subdomains from crawling.
(array of strings, optional, default: []): Regex patterns to exclude URLs with specific path patterns from crawling.
(string, optional, default: "advanced"): Depth of content extraction during crawl.
(boolean, optional, default: true): Whether to extract image URLs from the crawled pages.
(string, optional): Natural language instructions for the crawler for how to approach crawling the site.
(number, optional, default: 10): Total number of links the crawler will process starting from a single root URL before stopping.
(number, optional, default: 5): Max number of links to follow per level of the crawl tree (i.e., per page).
(number, optional, default: 1): Max depth of the crawl from the base URL. 0 means only the base URL, 1 means the base URL and links found on it, etc.
(array of strings, optional, default: []): Regex patterns to restrict crawling to specific domains or subdomains (e.g., "^docs\\.example\\.com$"). If crawlallowexternal is false (default) and this is empty, crawling is focused on the domain of the URL being crawled. This overrides that focus.
(array of strings, optional, default: []): Regex patterns to select only URLs with specific path patterns for crawling (e.g., "/docs/.").
(number, optional, default: 180): Timeout in seconds for each Tavily Crawl request.
(number, optional): For topic: "news", the number of days back from the current date to include search results.
(string, optional): Custom prompt for LLM documentation generation.
(array of strings, optional, default: []): A list of domains to specifically exclude from the search results.
(boolean or string, optional, default: false): Include an LLM-generated answer from Tavily based on search results.
(array of strings, optional, default: []): A list of domains to specifically include in the search results.
(boolean, optional, default: false): Include the cleaned and parsed HTML content of each initial search result.
(boolean, optional, default: false): Include image descriptions along with URLs from the initial search.
(boolean, optional, default: false): Include a list of query-related image URLs from the initial search.
(number, optional, default: 7): Maximum number of search results to retrieve and consider for crawling (1-20).
(string, optional): Path where generated research documents and images should be saved.
(string, required): The main research topic or question.
(string, optional, default: "advanced"): Depth of the initial Tavily search.
(number, optional, default: 60): Timeout in seconds for Tavily search requests.
(string, optional): Time range for search results (e.g., "d" for day, "w" for week, "m" for month, "y" for year).
(string, optional, default: "general"): Category for the Tavily search.