# Tavily MCP connector

The Tavily connector brings live web search and page content extraction into Claude, ChatGPT, Cursor and the Elaichi Agent, so each person can research the web as themselves through one governed endpoint while every search is logged.

Source: https://elaichi.ai/connectors/tavily/

## Facts

| | |
| --- | --- |
| Application | Tavily |
| Category | Artificial Intelligence |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Tavily builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | support@tavily.com |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Tavily is connected

- Search the web for Acme's latest funding news and summarize it
- Extract the pricing page from competitor.com and list the tiers
- Find recent reviews of our product and pull the top complaints

## Connect Tavily in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Tavily.
2. Optionally set Share with, then press Connect.
3. Approve it in Tavily. Tavily's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Tavily tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Tavily MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Tavily MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Tavily MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Tavily to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Tavily tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Tavily through Elaichi

### Research a prospect before the first call

Sales. Search the web for recent news, funding and leadership changes at an account, then pull the key facts from their site into your call prep.

### Track what competitors are publishing

Marketing. Ask for the latest pages, launches and pricing changes on competitor sites and get the page content extracted and summarized in one place.

### Find the vendor fix behind a customer error

Support. Search documentation and forums for the error message a customer reported, then extract the exact steps from the page that answers it.

### Gather market context for a roadmap decision

Product. Pull recent articles, reviews and release notes on a feature area and read the extracted content without opening twenty tabs.

### Check a candidate's public work

Recruiting. Search for talks, articles and open source a candidate has published, and extract the relevant pages for the hiring panel.

### Monitor regulatory and vendor announcements

Operations. Run a web search for new notices affecting your vendors or region and extract the page content so the team reads the source rather than a rumor.

## Elaichi vs Zapier MCP vs Composio for Tavily

All three can connect Tavily to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Tavily tools | Allow or restrict single Tavily tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Tavily call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Tavily to Claude?

Connect Tavily in Elaichi first: pick Tavily from the catalog and approve the OAuth sign-in when Tavily asks, with no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude asks you to sign in to Elaichi as yourself, and Tavily web search is available in your next chat.

### Does Tavily work with ChatGPT and Cursor as well as Claude?

Yes. Once Tavily is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Tavily once and every client you use picks it up.

### What can an AI agent actually do with Tavily?

With Tavily connected, an assistant can search the web for current pages on a topic, company or error message, and extract the readable content of a page you point it at. Exactly what is available depends on what your Tavily account has set up. Short, concrete asks such as finding the latest pricing page for a named company work better than long sentences.

### Does connecting Tavily give the AI everything in my Tavily account?

No. Every Tavily search and extraction runs under the access of the person who signed in, with whatever usage limits and settings their Tavily account has. Elaichi can narrow that further with roles and restrictions, and it can never widen access beyond what Tavily itself allows.

### Can my team share one Tavily connection?

Yes. One person connects Tavily in Elaichi and shares it with a team, and nobody else ever handles the Tavily credential. Each teammate still signs in to Elaichi as themselves, so the audit log names the person behind every Tavily search, not the person who connected the account.

### Can I limit what an agent is allowed to do in Tavily?

Yes. Restrictions in Elaichi apply per action, so you can allow Tavily web search while holding back page extraction, or the other way round, for a given team. A restricted Tavily action is never advertised to Claude, ChatGPT or Cursor at all, so no prompt, however worded, can reach it.

### What happens to a Tavily connection when someone leaves?

Offboarding a person in Elaichi ends their access to Tavily and every other connector at once, with nothing to revoke inside Tavily itself. A Tavily connection they shared keeps working for everyone else on the team. If you later disconnect Tavily in Elaichi, it disappears from Claude, ChatGPT, Cursor and every other client in one step.

### Does the Tavily MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Tavily is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Tavily?

Yes. Both let Claude, ChatGPT or Cursor use Tavily. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Tavily call.

### How is Elaichi different from Composio for Tavily?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Tavily: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.