# Tavily Search

> Use this tool when you need to perform web searches and retrieve structured results, including AI-generated answers, to access real-time information while maintaining a secure separation from external data sources. It solves problems such as conducting research, answering questions based on current information, and providing relevant search results. The Tavily Search tool accepts query inputs and returns formatted results, making it ideal for AI assistants requiring safe and controlled access to web data.

Canonical page: https://skillsregistry.net/skills/tomatio13-tavily-search  
JSON: https://api.skillsregistry.net/v1/skills/tomatio13-tavily-search

## Description

This Tavily search MCP server, developed by Tomatio13, provides an interface for AI assistants to perform web searches using the Tavily API. It enables AI agents to query Tavily and retrieve structured search results including AI-generated answers, URLs, and titles through a controlled MCP server. Built in Python, the implementation handles API authentication and request formatting. By leveraging Tavily's AI-powered search capabilities, this server allows AI systems to access real-time web information in a safe manner. It is particularly useful for AI assistants needing to conduct research, answer questions based on current information, or provide relevant search results while maintaining a clear separation between the AI model and external data sources. The implementation includes Docker support for easy deployment in various environments.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/tomatio13-tavily-search)
- **Repository:** <https://github.com/tomatio13/mcp-server-tavily>

## 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": "tomatio13-tavily-search"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tomatio13-tavily-search` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tomatio13-tavily-search/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