# tavily-ai/tavily-mcp

Production ready MCP server with real-time search, extract, map & crawl.

Repository: https://github.com/tavily-ai/tavily-mcp
Canonical: https://ross.abutalabs.com/products/tavily-mcp
Language: JavaScript
License: MIT
License Family: permissive
Last push: 2026-08-20T14:11:49+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 41
- inputs: {"age_days": 583, "days_push": 13, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2354, forks 290 (observed 2026-08-28T04:06:40.523913+00:00)

## What it is
A Model Context Protocol (MCP) server that exposes Tavily's web search, page extraction, site mapping, and crawling tools to AI assistants like Claude. It can run locally via Node.js or be accessed as a hosted remote MCP server with API key or OAuth authentication.

## Use cases
- give my AI assistant real-time web search
- extract content from web pages into Claude
- crawl an entire website and feed it to an LLM
- build a structured map of a website
- connect Claude Code or Claude Desktop to a search API
- add live web research to an MCP-compatible coding assistant

## When to choose
- you use an MCP client like Claude Desktop, Claude Code, or Cline and need live web search
- you want search, extraction, mapping, and crawling behind one protocol server
- you prefer a hosted remote MCP endpoint without local installation

## When to avoid
- you need a general-purpose scraper outside of LLM/MCP workflows
- you don't have or want a Tavily API key
- you need search results in a non-MCP application without writing integration code

## Facets
- artifact type: service
- maturity: active
- function: search-engine, web-scraping, mcp, http-server, parser
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cross-platform, cli
- tags: mcp-server, tavily, web-search, web-crawler, data-extraction, claude, real-time-search, site-mapping, ai-agents, search, nodejs, web-server

## Member repositories
- tavily-ai/tavily-mcp (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:40.523913+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:36:28.983836+00:00, confidence not recorded.
  - readme: https://github.com/tavily-ai/tavily-mcp (fetched 2026-08-28T04:06:40.523913+00:00, sha 9de205729aa4)
  - registry_npm: https://registry.npmjs.org/tavily-mcp (fetched 2026-08-29T10:17:23.973733+00:00, sha 1e9ee84707d4)
- Data as of 2026-08-30T08:39:29.467469+00:00.