Web Scout
deep-research-tool
Performs extensive web research using Tavily Search and Crawl. Returns aggregated JSON data including the query, search summary (if any), detailed research findings, and documentation instructions. The documentation instructions will guide you on how the user wants the research data to be formatted into markdown.
Remote pinkpixel-dev/deep-research-mcp
Other tools also called deep-research-tool?
See providers with this name
Input Schema
{
"type": "object",
"properties": {
"days": {
"type": "number",
"description": "For 'news' topic: number of days back from current date to include results."
},
"query": {
"type": "string",
"description": "The main research topic or question."
},
"topic": {
"enum": [
"general",
"news"
],
"type": "string",
"default": "general",
"description": "Category for the Tavily search ('general' or 'news')."
},
"time_range": {
"type": "string",
"description": "Time range for search results (e.g., 'd' for day, 'w' for week, 'm' for month, 'y' for year)."
},
"crawl_limit": {
"type": "number",
"default": 10,
"description": "Total links crawler will process per root URL (1-20). Can be set via CRAWL_LIMIT environment variable."
},
"search_depth": {
"enum": [
"basic",
"advanced"
],
"type": "string",
"default": "advanced",
"description": "Depth of the initial Tavily search ('basic' or 'advanced')."
},
"crawl_timeout": {
"type": "number",
"default": 180,
"description": "Timeout in seconds for Tavily crawl requests. Can be set via CRAWL_TIMEOUT environment variable."
},
"include_answer": {
"anyOf": [
{
"type": "boolean"
},
{
"enum": [
"basic",
"advanced"
],
"type": "string"
}
],
"default": false,
"description": "Include an LLM-generated answer from Tavily search (true implies 'basic')."
},
"search_timeout": {
"type": "number",
"default": 60,
"description": "Timeout in seconds for Tavily search requests. Can be set via SEARCH_TIMEOUT environment variable."
},
"crawl_max_depth": {
"type": "number",
"default": 1,
"description": "Max crawl depth from base URL (1-2). Higher values increase processing time significantly. Can be set via CRAWL_MAX_DEPTH environment variable."
},
"crawl_categories": {
"type": "array",
"items": {
"type": "string"
},
"default": [],
"description": "Filter crawl URLs by categories (e.g., 'Blog', 'Documentation')."
},
"chunks_per_source": {
"type": "number",
"default": 3,
"maximum": 3,
"minimum": 1,
"description": "For 'advanced' search: number of content chunks from each source (1-3)."
},
"crawl_max_breadth": {
"type": "number",
"default": 10,
"description": "Max links to follow per page level during crawl (1-10)."
},
"crawl_instructions": {
"type": "string",
"description": "Natural language instructions for the crawler."
},
"crawl_select_paths": {
"type": "array",
"items": {
"type": "string"
},
"default": [],
"description": "Regex for URLs paths to crawl (e.g., '/docs/.*')."
},
"max_search_results": {
"type": "number",
"default": 7,
"maximum": 20,
"minimum": 1,
"description": "Max search results to retrieve for crawling (1-20). Can be set via MAX_SEARCH_RESULTS environment variable."
},
"crawl_exclude_paths": {
"type": "array",
"items": {
"type": "string"
},
"default": [],
"description": "Regex for URL paths to exclude."
},
"crawl_extract_depth": {
"enum": [
"basic",
"advanced"
],
"type": "string",
"default": "basic",
"description": "Extraction depth for crawl ('basic' or 'advanced')."
},
"crawl_allow_external": {
"type": "boolean",
"default": false,
"description": "Allow crawler to follow links to external domains."
},
"crawl_include_images": {
"type": "boolean",
"default": false,
"description": "Extract image URLs from crawled pages."
},
"crawl_select_domains": {
"type": "array",
"items": {
"type": "string"
},
"default": [],
"description": "Regex for domains/subdomains to crawl (e.g., '^docs\\.example\\.com$'). Overrides auto-domain focus."
},
"documentation_prompt": {
"type": "string",
"description": "Optional. Custom prompt for LLM documentation generation. Overrides 'DOCUMENTATION_PROMPT' env var and default. If none set, a comprehensive default is used."
},
"crawl_exclude_domains": {
"type": "array",
"items": {
"type": "string"
},
"default": [],
"description": "Regex for domains/subdomains to exclude."
},
"hardware_acceleration": {
"type": "boolean",
"default": false,
"description": "Try to use hardware acceleration (WebGPU) if available."
},
"include_search_images": {
"type": "boolean",
"default": false,
"description": "Include image URLs from initial search results."
},
"exclude_domains_search": {
"type": "array",
"items": {
"type": "string"
},
"default": [],
"description": "List of domains to specifically exclude from search."
},
"include_domains_search": {
"type": "array",
"items": {
"type": "string"
},
"default": [],
"description": "List of domains to specifically include in search."
},
"include_raw_content_search": {
"type": "boolean",
"default": false,
"description": "Include cleaned HTML from initial search results."
},
"include_search_image_descriptions": {
"type": "boolean",
"default": false,
"description": "Include image descriptions from initial search results."
}
}
}