---
title: "Tavily: setup for Claude, Cursor, Codex · DotsAgent"
description: "Search, extract, crawl and map websites through Tavily's agent-oriented search API, hosted or run locally. Set up Tavily in 13 MCP clients."
url: https://dotsagent.io/mcp/servers/tavily
---

Search and docs · Tavily

# Set up Tavily

Search, extract, crawl and map websites through Tavily's agent-oriented search API, hosted or run locally.

- **Publisher**: Tavily Official
- **Hosted endpoint**: `https://mcp.tavily.com/mcp`
- **Run locally**: `npx -y tavily-mcp@latest`
- **Transports**: streamable-http, stdio
- **Authentication**: OAuth, or an API key in the URL when hosted; TAVILY_API_KEY when run locally.
- **Environment**: `TAVILY_API_KEY`
- **What it can touch**: Read-only.
- **Licence**: MIT
- **Source**: [github.com/tavily-ai/tavily-mcp](https://github.com/tavily-ai/tavily-mcp)
- **Status**: Active

## Install

The vendor hosts this server, so you only add its URL and nothing runs on your machine. If it needs authentication, the row above says how; OAuth servers prompt you on first connection.

### Claude Code

`shell`

```
claude mcp add --transport http --scope project tavily https://mcp.tavily.com/mcp
```

### Cursor

`.cursor/mcp.json`

```
{
  "mcpServers": {
    "tavily": {
      "url": "https://mcp.tavily.com/mcp"
    }
  }
}
```

### Codex

`~/.codex/config.toml`

```
[mcp_servers.tavily]
url = "https://mcp.tavily.com/mcp"
```

### Run it locally instead (Cursor)

`.cursor/mcp.json`

```
{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp@latest"
      ],
      "env": {
        "TAVILY_API_KEY": "${env:TAVILY_API_KEY}"
      }
    }
  }
}
```

[Config for other clients →](https://dotsagent.io/mcp/config#add=tavily)

## Other servers in search and docs

- [Fetch](https://dotsagent.io/mcp/servers/fetch): Fetches a web page and converts it to Markdown so the model can read it. Part of the MCP project's reference set.

- [AWS Knowledge](https://dotsagent.io/mcp/servers/aws-knowledge): AWS-hosted search over AWS documentation, blog posts, What's New entries and regional availability.

- [Microsoft Learn](https://dotsagent.io/mcp/servers/microsoft-learn): Search and fetch official Microsoft and Azure documentation and code samples.

- [Brave Search](https://dotsagent.io/mcp/servers/brave-search): Brave's own server for web, news, image, video and local search through the Brave Search API.

- [Exa](https://dotsagent.io/mcp/servers/exa): Neural web search, page contents and code-context search for agents, hosted by Exa or run locally with an API key.

- [Firecrawl](https://dotsagent.io/mcp/servers/firecrawl): Scrape, crawl, search and extract structured data from websites as Markdown or JSON.

## Sources

1. [github.com](https://github.com/tavily-ai/tavily-mcp)/tavily-ai/tavily-mcp

Independent reference for people who build AI agents. Not affiliated with any vendor named here.

© 2026 DotsAgent · Facts checked October 1, 2026