Search and Retrieval APIs
Use Tavily with CrewAI
Tavily connects to CrewAI through a built in by the framework vendor path (crewai_tools TavilySearchTool). This page records what that connection looks like and links the evidence behind it.
Pairing facts
Why this pairing
A web access API built for AI agents: search, extract, map, crawl, and research endpoints behind one key.
Best for: Agents that need current web facts with cited results Research workflows that combine search with page extraction Teams that want one vendor for search and fetching
Not ideal for: Fully offline or self-hosted stacks High-volume crawling without a credit budget
Configuration
pip install 'crewai[tools]' tavily-python
from crewai_tools import TavilySearchTool
tavily_tool = TavilySearchTool()Source: https://docs.crewai.com/v1.15.18/en/tools/search-research/tavilysearchtool. Examples use placeholders only.
Evidence
The CrewAI docs page documents TavilySearchTool as an interface to the Tavily Search API for CrewAI agents and shows installation with crewai[tools] and tavily-python.
https://docs.crewai.com/v1.15.18/en/tools/search-research/tavilysearchtool
Compatibility here means the cited page documents the pairing. It does not mean AgentsUse benchmarked the combination or that every version works unchanged. Pin versions, run the tool on a small job first, and review the first outputs before widening access.
Watch for
- Metered by credits, so unattended crawl loops need spending controls.
- A managed service: no self-hosted fallback when Tavily is down or a source blocks it.