Tavily
The web-access layer for agents — Search, Extract, Crawl, Map, and Research APIs purpose-built for LLMs, behind one key, with a hosted MCP server.
Tavily packages agent web access as one API: Search tuned for LLM consumption (vendor-claimed 180ms p50), Extract for clean page content, Crawl and Map for site traversal, and a Research endpoint for multi-step investigations — plus SDKs and a hosted MCP server (mcp.tavily.com). Freemium: 1,000 free credits monthly, no card, then pay-as-you-go.
Tavily's framing is exactly the 2026 need: not "a search engine you can call" but the web-access layer for agents — search, extraction, crawling, and multi-step research as one credit pool behind one key, with latency treated as a feature.
Highlights
- Search built for agents — LLM-ready results at ultra-fast, fast, basic or advanced depth, with a vendor-claimed 180ms p50 that matters when search sits inside an agent loop.
- Extract, Crawl, Map — clean content from URLs, instruction-guided site traversal, and URL discovery: the ingestion half, included.
- Research endpoint — multi-step investigations (pro/mini tiers) as a single API call, for when one search isn't an answer.
- Hosted MCP server —
mcp.tavily.com/mcp/makes search, extract, map and crawl a one-liner in Claude Code and friends. - Drop-in ecosystem — Python/JS SDKs and first-class integrations across OpenAI, Anthropic, LangChain, plus marketplace placements (Databricks) and a JetBrains integration.
In an AI-assisted workflow
pip install tavily-python # or: npm i @tavily/core
# client = TavilyClient(api_key="tvly-..."); client.search("…", search_depth="advanced")In agent stacks it's typically the web tool: the agentic-RAG searcher, the research agent's eyes, the freshness layer RAG over static corpora lacks.
WARNING
Same caution as every web tool: fetched pages are untrusted input to your model — indirect prompt injection rides in on search results. Treat content as data, and gate any tools that act on it.
Good to know
The company comes from the team behind open-source GPT Researcher and raised a $25M Series A in August 2025; Nebius Group then acquired it, closing on February 19, 2026 without disclosing a price, and Tavily continues under its own brand as Tavily by Nebius. It now claims 2M+ developers. SDKs and the MCP server are MIT; the API is the product. Credits aren't 1:1 with calls — budget for advanced/research multipliers. Field positioning against Exa and Firecrawl: Getting Web Data into AI Agents.
Frequently asked questions
- How is Tavily different from Exa and Firecrawl?
- Breadth-in-one-key versus specialist depth. Exa's center is semantic search quality and entity research (Websets); Firecrawl's is industrial-strength scraping and crawling. Tavily bundles credible versions of search + extract + crawl + research behind a single key and credit pool — the convenience pick for agents that need all of it, with speed as its search pitch.
- Is Tavily free to start?
- Yes — as of September 2026 the free Researcher plan includes 1,000 API credits every month with no credit card, and beyond that pay-as-you-go is $0.008 per credit, with larger plans and Enterprise above it. Mind the credit math: basic search costs 1 credit and advanced 2, extract bills 1 credit per 5 URLs (2 on advanced), and the Research endpoint is dynamic — 4 to 110 credits per request on mini, 15 to 250 on pro.
- How do I use Tavily from Claude Code?
- Its hosted MCP server: claude mcp add tavily-remote-mcp --transport http https://mcp.tavily.com/mcp/ (OAuth, or append your tvly- API key as a parameter). It exposes the search/extract/map/crawl tools; a local npm server (tavily-mcp) exists too.
Filed under
search · web-data · api · agents · mcp
Related
- Getting Web Data into AI Agents: Search & Scraping APIs ComparedThe agent web-data layer — Exa for semantic search, Firecrawl for extraction at scale, Tavily for all-in-one, Jina Reader for zero-setup — and how they compose.
- Jina ReaderPrepend r.jina.ai/ to any URL and get LLM-ready markdown — JS rendering, PDFs and Office docs, image captioning, and s.jina.ai for read-the-results search.
- ExaThe search engine built for AIs — semantic web search, page contents, Websets, and research APIs, plus a hosted MCP server.
- FirecrawlThe API to search, scrape, and crawl the web for AI — clean Markdown out of any site, LLM-powered extraction, and a first-class MCP server.
- Adding MCP Servers to Claude Code: Local, Remote, and Project-ScopedThe complete claude mcp add reference — stdio vs HTTP transports, local/project/user scopes, .mcp.json with env expansion, OAuth via /mcp, and the gotchas.
- RAG (Retrieval-Augmented Generation)RAG retrieves relevant documents from your own data and injects them into an LLM's prompt at query time, grounding answers in facts the model wasn't trained on.
- Jina Reader API: r.jina.ai and s.jina.ai Headers, Examples, and LimitsHow to use the Jina Reader API: r.jina.ai and s.jina.ai quickstart, every documented request header, curl recipes, rate limits, MCP setup, and self-hosting.
- Web Research PipelineRun a structured web-research pass on a question: plan the searches, find sources via search APIs, fetch and read the best ones, cross-check claims, and synthesize a cited answer — with source quality and disagreements surfaced honestly. Use for 'research X and tell me what's actually true' tasks that need more than one search and less than a day.