How do I find my Tavily API Key?

Log in to your [**Tavily dashboard**](https://tavily.com/), and you will find your API Key on the overview page. Copy and paste it below.

What is Search Context vs Web Search?

Search Context is optimized for direct ingestion by LLMs, providing a denser format of information, while Web Search provides standard curated results with snippets and scores.

Can the agent extract content from any website?

Yes. The `extract_content` tool allows your agent to retrieve the cleaned main text from any accessible URL, bypassing ads and navigation elements for structured analysis.

Tavily MCP Server for Google ADK 6 tools — connect in under 2 minutes

Name: Tavily
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 6 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Tavily as an MCP tool provider through the Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token — get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="tavily_agent",
    instruction=(
        "You help users interact with Tavily "
        "using 6 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Tavily MCP Server

Empower your AI agent to orchestrate your entire web research workflow with Tavily, the search engine built specifically for AI agents. By connecting Tavily to your agent, you transform complex information retrieval into a natural conversation. Your agent can instantly audit search context, retrieve direct AI answers, and extract clean content from any URL without you ever touching a browser. Whether you are conducting deep market research or monitoring real-time news, your agent acts as a real-time research assistant, ensuring your intelligence is always grounded in optimized, high-quality data.

Google ADK natively supports Tavily as an MCP tool provider — declare the Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 6 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

AI-Optimized Search — Query the web for results specifically curated for LLM consumption, including snippets and relevancy scores.
Direct Answers — Retrieve concise AI-generated answers for complex search queries to skip manual data synthesis.
Content Extraction — Extract clean, readable text from any list of URLs to maintain a structured view of web content.
Real-time News Oversight — Monitor current events through specialized news search to stay on top of industry updates.
Visual Discovery — Search for high-quality images optimized for AI agents to maintain visual context in your research.

The Tavily MCP Server exposes 6 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Tavily to Google ADK via MCP

Follow these steps to integrate the Tavily MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 6 tools from Tavily via MCP

Why Use Google ADK with the Tavily MCP Server

Google ADK provides unique advantages when paired with Tavily through the Model Context Protocol.

Google ADK natively supports MCP tool servers — declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Tavily

Production-ready features like session management, evaluation, and deployment come built-in — not bolted on

Seamless integration with Google Cloud services means you can combine Tavily tools with BigQuery, Vertex AI, and Cloud Functions

Tavily + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Tavily MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Tavily and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Tavily tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Tavily regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Tavily

Tavily MCP Tools for Google ADK (6)

These 6 tools become available when you connect Tavily to Google ADK via MCP:

extract_content

Extract clean content from specific URLs

get_answer

Get a direct AI answer for a search query

get_search_context

Get search context for a query (optimized for LLMs)

search_images

Search for images optimized for AI

search_news

Search for real-time news results

search_web

Search the web for AI-optimized results

Example Prompts for Tavily in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Tavily immediately.

"Search for the latest breakthroughs in 'Quantum Computing' using Tavily."

"Get an AI answer for 'How does photosynthesis work?'."

"Extract content from https://vinkius.com."

Troubleshooting Tavily MCP Server with Google ADK

Common issues when connecting Tavily to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Tavily + Google ADK FAQ

Common questions about integrating Tavily MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.