Use Tavily from Claude
Add the Tavily connection to a Space that runs Claude, then use it from every channel in that Space.
ConnectorTavily
Tavily integration for Claude and Codex
Create a Tavily connection, then control which Spaces can use its approved tools and data without pasting credentials into prompts or threads.
CategoryAnalytics & Data
Use Tavily from Codex
Add the Tavily connection to a Space that runs Codex, then use it from every channel in that Space.
Use Tavily from Sidekick
Connect your own OpenClaw to Sidekick while Type provides the conversations, permissions, connections, skills, and automations.
Analytics & Data
What the Tavily connector can do
Tavily offers search and data retrieval solutions, helping teams quickly locate and filter relevant information from documents, databases, or web sources
One connection, many Spaces
Connect Tavily once, then decide which Spaces can use it in threads, skills, automations, and coding work.
Representative actions
- Tavily crawl
Tool to perform intelligent graph-based website crawling with parallel path exploration and content extraction. Use when you need to traverse and extract content from multiple pages of a website following specific patterns or instructions. Supports depth/breadth controls, domain filtering, and natural language instructions for guided crawling.
- Tavily extract
Tool to extract and parse web page content from specified URLs using Tavily's extract endpoint. Use when you need to retrieve clean, structured content from web pages with optional image extraction and content reranking based on query relevance.
- Get Tavily usage
Tool to retrieve API key and account usage statistics from Tavily. Use when you need to check credit consumption, limits, and per-endpoint usage for search, extract, crawl, map, and research operations.
- Tavily map website
Tool to map a website and discover its pages. Use when you need to scan a website and get a structured list of URLs/pages it contains without extracting full content.
- Tavily search
Use this to perform a web search via the Tavily API; offers controls for search depth, content types, result count, and domain filtering. Requires an active Tavily connection (401 = auth failure). Rate limit: ~2 req/s; apply exponential backoff on HTTP 429. Results are nested under response_data.results (not a flat list). Subject to HTTP 429 on rapid bursts.
Connection
API and auth details
Tavily exposes web search, extract, crawl, map, and research APIs at api.tavily.com using bearer API-key authentication.
- Source
- Official docs verified 2026-06-03
- Auth schemes
- Bearer token
- Base URL
- https://api.tavily.com
- Official site
- https://docs.tavily.com
Official endpoint references
Source links
FAQ
Questions people ask before connecting Tavily
Can Claude use Tavily?
Yes. Add a Tavily connection to a Space that runs Claude, then use its approved tools and data from any channel in that Space.
Can Codex work with Tavily through Type?
Yes. Add a Tavily connection to a Space that runs Codex, then use its approved tools and data from any channel in that Space.
Is this the same as a Tavily MCP server?
Not exactly. Type uses connectors and connections to give selected Spaces access to approved app tools and data. Some connectors use hosted MCP, while others use OAuth, API keys, service accounts, or custom APIs.
More analytics & data connectors
Perplexity AI provides conversational AI models for generating human-like text responses
SerpApi provides a real-time API for structured search engine results, allowing developers to scrape, parse, and analyze SERP data for SEO and research
Firecrawl automates web crawling and data extraction, enabling organizations to gather content, index sites, and gain insights from online sources at scale