# Tavily

> Use this tool when you need to perform web searches and retrieve relevant information through a standardized interface, solving problems such as fact-checking and research tasks that require up-to-date information. It takes in search queries as input and returns relevant results as output, enabling AI systems to incorporate web search functionality without directly managing API complexities. This integration is particularly useful for scenarios requiring real-time information retrieval, enhancing AI systems with web search capabilities.

Canonical page: https://skillsregistry.net/skills/mcp2everything-tavily  
JSON: https://api.skillsregistry.net/v1/skills/mcp2everything-tavily

## Description

This Tavily integration for MCP, developed by an unknown author, provides a bridge between AI assistants and the Tavily search API. It enables AI systems to perform web searches and retrieve relevant information through a standardized MCP interface. The implementation uses Python and leverages libraries like FastMCP and Tavily's official Python SDK to handle API interactions and request processing. By abstracting Tavily's search capabilities into MCP-compatible endpoints, it allows AI assistants to easily incorporate web search functionality without directly managing API complexities. This integration is particularly useful for scenarios requiring up-to-date information retrieval, fact-checking, or research tasks, enhancing AI systems with real-time web search capabilities.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/mcp2everything-tavily)
- **Repository:** <https://github.com/mcp2everything/mcp2tavily>

## 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": "mcp2everything-tavily"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mcp2everything-tavily` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mcp2everything-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