Tavily Web
Access and extract data from live websites using advanced web scraping and intelligent content understanding.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add tavily-web npx -- -y @trustedskills/tavily-web
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"tavily-web": {
"command": "npx",
"args": [
"-y",
"@trustedskills/tavily-web"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The tavily-web skill enables AI agents to search and retrieve information from the web using Tavily's API. It allows for real-time data fetching, making it useful for tasks that require up-to-date or external information.
When to use it
- To gather current news or event updates during a conversation.
- When an AI agent needs to verify facts or look up specific details from the web.
- For research tasks where access to recent online content is necessary.
Key capabilities
- Real-time web search using Tavily's API
- Retrieval of relevant information based on user queries
- Integration with AI agents for dynamic data fetching
Example prompts
- "Find the latest news about climate change."
- "What was the outcome of yesterday’s World Cup match?"
- "Look up the current stock price of Apple."
Tips & gotchas
- Ensure you have a valid Tavily API key configured before using this skill.
- Be mindful of rate limits or usage caps imposed by the Tavily service.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.