# Tavily MCP for AI Agents | FlyMy.AI

> Tavily MCP for Claude, Codex and Cursor through FlyMy.AI. Real-time web search & extraction. 6 actions, no key needed.

Page: https://flymy.ai/mcp/tavily/

MCP / Web research

# Tavily MCP

Real-time web search & extraction. Connect it to Claude, Codex, Cursor or any MCP client through one FlyMy.AI MCP.

[Connect Tavily](https://flymy.ai/mcp/tavily/#connect) [What it can do](https://flymy.ai/mcp/tavily/#actions)

Ready to use: no key, 6 actions, Web research, Top 20 on FlyMy.AI

Ask your agent

```
Search the web for this week's news about EU AI Act enforcement and give me five links with one-line summaries.
```

Paste it into an assistant connected to FlyMy.AI. The agent picks the actions.

## What Tavily MCP can do

6 actions in the FlyMy.AI catalog, the most used first. Your agent finds them through search_tools and calls the one the task needs.

| Action | What it does |
|---|---|
| `tavily_search_advanced` | Tavily advanced web search. Same as tavily_search, but always uses search_depth='advanced' for deeper, higher-quality results. |
| `tavily_search` | Tavily web search. Provide a natural-language query; returns a list of results with title, url, and snippet. |
| `tavily_extract` | Extract and clean the main text content from a single web page by URL. |
| `tavily_site_search` | Tavily site-specific search. Restricts results to a given domain using a site:example.com style query. |
| `tavily_search_with_images` | Tavily web search preferring results with images. |
| `tavily_crawl` | Lightweight Tavily-based crawl: performs a broader search (optionally restricted to a single site) and aggregates multiple results. |

## Ask your agent

Requests to paste as they are. Each one runs on the actions named under it.

**“Search the web for this week's news about EU AI Act enforcement and give me five links with one-line summaries.”** uses `tavily_search`

**“Read https://example.com/pricing and put the plan names and monthly prices in a table.”** uses `tavily_extract`

**“Search only docs.stripe.com for how to issue a partial refund and quote the steps.”** uses `tavily_site_search`

**“Do a deep search on open-source vector databases released this year and compare them in a table with sources.”** uses `tavily_search_advanced`

## Connect Tavily in a minute

One MCP for every integration. Add it once, then every MCP in the catalog is a request away.

1. 01 ### Add FlyMy.AI Add the FlyMy.AI MCP to your assistant with one of the commands below and sign in. No key to copy.
2. 02 ### Nothing to connect Tavily runs on the FlyMy.AI platform key: no account and no key of yours. Calls are billed to your FlyMy.AI balance.
3. 03 ### Ask Paste a request from this page. Every run shows what it cost.

Claude Code

```
claude mcp add --transport http flymyai https://mcp-agents.flymy.ai/mcp
```

Then run /mcp in Claude Code and sign in.

Codex

```
codex mcp add flymy --url https://mcp-agents.flymy.ai/mcp
```

Then run codex mcp login flymy to sign in.

claude.ai and Claude Desktop

```
https://mcp-agents.flymy.ai/mcp
```

Settings, Connectors, Add custom connector: paste this URL.

## Pay per run

Calls run on FlyMy.AI's key and are billed per call to your FlyMy.AI balance at the published rate. No seats and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## More Web research MCPs

Search the web, read pages, run a real browser and pull structured data.

### Browser Use

Browser Use Cloud - run real browser tasks on browser-use.com

14 actions / no key

Link: https://flymy.ai/mcp/browser-use/

### Akta

Private-company data & news signals - enrichment, headcount, reviews, jobs, traffic

14 actions / no key

Link: https://flymy.ai/mcp/akta/

### Hacker News

Hacker News is a tech-focused news aggregator by Y Combinator, featuring user-submitted stories and discussions on startups, programming, and emerging trends

6 actions / no key

Link: https://flymy.ai/mcp/hackernews/

### Firecrawl

Firecrawl web scraping to clean agent-ready data: scrape a page to markdown or JSON, crawl a site, map its urls, search the web

13 actions / your API key

Link: https://docs.flymy.ai/mcp/firecrawl

### Agentql

AgentQL is a suite of tools designed to connect AI agents to the web, enabling web interaction and structured data extraction through a specialized query...

3 actions / your API key

Link: https://docs.flymy.ai/mcp/apps/agentql

### Agenty

Agenty is a web scraping and automation platform that enables users to extract data, monitor changes, and automate browser tasks without coding

40 actions / your API key

Link: https://docs.flymy.ai/mcp/apps/agenty

## Go to the source

[Tavily in the docs →](https://docs.flymy.ai/mcp/tavily), [Tavily connection settings →](https://app.flymy.ai/mcp-configs#tavily), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI platform catalog of 2026-10-28: name, description, actions and setup as the platform lists them. Examples are requests to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.
