Browse
🔍

Tavily

🟢Safe
Search & Web

Search engine for AI agents (search + extract) powered by Tavily

STEP 1

Understand what it does

Tell your agent things like:

→“use tavily”
→“search the web”
→“find information”
→“look up”
PERMISSIONS

What this capability can access

This capability requires the following permissions:

🌐
Read External Data
Fetches data from external sources
STEP 2

Set it up

Available on 2 platforms. Pick yours:

MCP (Model Context Protocol)Docs

Add to your MCP client configuration:

{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-tavily"]
    }
  }
}
LangChainDocs
$ pip install langchain-community
from langchain_community.tools import ...
# See docs for specific import
STEP 3

Go deeper

Full documentation and source code

View Source / DocsExplore Search & Web

Add to your README

Show that your tool is listed on AgentSift

Tavily trust score on AgentSift
[![AgentSift](https://agentsift.com/api/badge/capability/tavily)](https://agentsift.com/capabilities/tavily)

Options: ?style=flat-square for square corners, ?score=false for simple “listed” badge

#mcp#search#agent-tool

Related capabilities

🔍

Google Ads

MCP server acting as an interface to the Google Ads, enabling programmatic access to Google Ads data and management features.

🔍

Google News

Google News search capabilities with automatic topic categorization and multi-language support via SerpAPI integration.

🔍

Google Pse

A Model Context Protocol (MCP) server providing access to Google Programmable Search Engine (PSE) and Custom Search Engine (CSE).

🔍

Google Research Mcp

Perform advanced web research using Google Search, with intelligent content extraction and multi-source synthesis.

🔍

Google Search Engine

A server for Google search and webpage content extraction, built on Cloudflare Workers with OAuth support.

🔍

Google Web Search

Provides Google Web Search functionality using the Gemini API. Requires a Google API Key or OAuth credentials.