# Tavily Search

> Use this tool when you need to integrate AI-powered search capabilities into your workflow, enabling natural language-driven research and information retrieval. It solves problems of finding relevant web information and provides a streamlined interface for performing searches with features like result caching and AI-generated summaries. Ideal for AI assistants and developers, it accepts search queries as input and outputs traditional search results along with AI-generated summaries.

Canonical page: https://skillsregistry.net/skills/it-beard-tavily  
JSON: https://api.skillsregistry.net/v1/skills/it-beard-tavily

## Description

This Tavily MCP server, developed by the Tavily MCP Server Contributors, integrates Tavily's AI-powered search capabilities into MCP-compatible workflows. Built with TypeScript and leveraging the @modelcontextprotocol/sdk, it provides a streamlined interface for performing web searches through Claude Desktop and other MCP clients. The implementation offers both basic and advanced search depths, result caching, and persistent storage of search history. It stands out by providing AI-generated summaries alongside traditional search results. This server is particularly useful for AI assistants and developers looking to incorporate up-to-date web information into their applications, enabling natural language-driven research and information retrieval.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/it-beard-tavily)
- **Repository:** <https://github.com/it-beard/tavily-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "it-beard-tavily"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/it-beard-tavily` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/it-beard-tavily/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt