--- title: "tavily" description: "Search, extract, crawl, map, and research the web with Tavily MCP tools and bundled skills for research, enrichment, monitoring, and integrations." canonical: https://agentpluginsdirectory.com/plugins/tavily last-updated: 2026-09-09 --- # tavily Search, extract, crawl, map, and research the web with Tavily MCP tools and bundled skills for research, enrichment, monitoring, and integrations. - Slug: tavily - Publisher: Tavily - Repository: https://github.com/tavily-ai/tavily-power - Manifest: plugin.json - Version: 1.0.1 - Category (editorial): other - Skills: 20 (academic-scientific-research, build-entity-list, fill-missing-fields, investment-research-briefs, migrate-to-tavily, past-research-search, product-competitor-intelligence, sales-account-intelligence, tavily-best-practices, tavily-cli, tavily-crawl, tavily-dynamic-search, tavily-extract, tavily-map, tavily-mcp, tavily-research, tavily-search, threat-intelligence-enrichment, vendor-risk-kyc-screening, watch-for-changes) - MCP servers: 1 (tavily) - Stars: 0 - Repository created: 2026-03-13 - Repository last pushed: 2026-09-08 - Publisher type: Organization - Listing: https://agentpluginsdirectory.com/plugins/tavily - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What tavily does, in the publisher's words Search the web, extract content from URLs, crawl websites, and conduct AI-powered research, all from within Kiro. This power gives Kiro AI agents access to Tavily's LLM-optimized APIs for real-time web data. Tavily is a search engine and API designed specifically for AI agents and LLMs. It delivers real-time web data, search results, page content, full-site crawls, and multi-source research reports, in formats optimized for agent consumption, with relevance scoring and metadata built in. Tavily powers the retrieval layer for thousands of AI applications, from RAG pipelines to autonomous research agents. - Web Search: Find current information with relevance scoring, domain filtering, and time-range controls - Content Extraction: Pull clean markdown or text from any URL, including JavaScript-rendered pages From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/tavily-ai/tavily-power/HEAD/README.md ## Skills - academic-scientific-research: Find, screen, and synthesize academic papers, scientific literature, technical reports, preprints, clinical or biomedical publications, and evidence around a research question. Use when the user asks to find papers, summarize literature, compare methods, identify seminal or recent work, extract cla… - build-entity-list: Build a structured, deduplicated list of entities matching a description you give, companies, people, products, laws, anything, instead of a pile of articles you have to read yourself. Use this skill when the user doesn't have a starting list and wants one built from criteria, or says "find all com… - fill-missing-fields: Fill in missing data on a list of companies, people, or products by looking each one up on the web. Use this skill when the user has a spreadsheet, CSV, or list of names and wants missing fields added, CEO, funding raised, headquarters, employee count, contact info, pricing, or any other web-discov… - investment-research-briefs: Create concise investment research briefs, company memos, sector snapshots, portfolio monitoring updates, earnings/news summaries, risk and catalyst briefs, and market thesis support. Use when the user asks for an investor-focused brief on a company, sector, public/private market, comparable set, o… - migrate-to-tavily: Migrate an existing integration from a competing web-search/research API, Exa, Firecrawl, Perplexity, or Parallel, over to Tavily, preserving behavior while swapping calls, imports, environment variables, and error handling. Use this skill when the user has working code against a competitor's SDK a… - past-research-search: Look up a past research run by what you asked, not by remembering its run ID. Use this skill when the user wants to revisit a previous tavily-research task and doesn't have the request_id handy, or says "what did that research on X find again", "pull up my last research on Y", "show me past researc… - product-competitor-intelligence: Research competitor products, SKUs, pricing, packaging, positioning, feature comparisons, product catalogs, category pages, retailer listings, marketplace data, and market intelligence. Use when the user asks for competitor SKU discovery, product data enrichment, pricing/spec extraction, product co… - sales-account-intelligence: Build sales-ready account intelligence for companies, prospects, customers, partners, and target buyers. Use when the user asks for sales prep, account brief, meeting prep, buyer research, expansion signals, customer intelligence, trigger events, executive context, outreach angles, or market/accoun… - tavily-best-practices: Build production-ready Tavily integrations with best practices baked in. Reference documentation for developers using coding assistants (Claude Code, Cursor, etc.) to implement web search, content extraction, crawling, and research in agentic workflows, RAG systems, or autonomous agents. - tavily-cli: Set up, authenticate, update, troubleshoot, or choose between Tavily CLI web commands. Use when the user asks about the Tavily CLI, installing Tavily skills, first-time setup, authentication, keyless limits, CLI updates, or which Tavily command to use. For an ordinary web task, use the specific sea… - tavily-crawl: Crawl websites and extract content from multiple pages via the Tavily CLI. Use this skill when the user wants to crawl a site, download documentation, extract an entire docs section, bulk-extract pages, save a site as local markdown files, or says "crawl", "get all the pages", "download the docs",… - tavily-dynamic-search: Programmatic Tavily search with context isolation. Use when web search or extraction will return large results that need filtering, deduplication, or multi-step triage before they enter the model context. Use tavily-search for ordinary lookups and tavily-research for end-to-end cited synthesis. - tavily-extract - tavily-map - tavily-mcp - tavily-research - tavily-search - threat-intelligence-enrichment - vendor-risk-kyc-screening - watch-for-changes Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized. ## MCP servers - tavily: transport: streamable-http; url: https://mcp.tavily.com/mcp Read from the plugin's own mcp.json. Environment variable names only, never values.