How to Use the Exa AI MCP in Google ADK

Q: How do I register the Exa AI MCP Server tools in Google ADK?

Instantiate McpToolset using the Streamable HTTP parameters pointing to your Vinkius endpoint. Pass this toolset directly to your LlmAgent to let Gemini auto-discover the available search capabilities.

Q: How does the Exa AI integration handle Gemini's long context windows in Google ADK?

The getcontents tool strips out bloated script tags and styling markup to deliver dense, readable text. This allows Gemini to analyze dozens of full-length articles simultaneously without hitting token limits.

Connect Gemini's million-token context with real-time web data using Google ADK and Exa AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa AI MCP to Google ADK

Create your Vinkius account to connect Exa AI to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Exa AI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic discovery via Google ADK

`search_web` delivers conceptual search results directly to your Google ADK pipeline. Instead of relying on rigid keyword matching, Gemini uses this tool to find web pages that match the actual intent of your query. This MCP integration feeds clean data into Gemini's massive context window. You can pull massive datasets without worrying about formatting errors or broken links.

Massive content ingestion for deep reasoning

`search_with_contents` combines web search and raw text extraction into a single API call for Google ADK. Your agent receives the search results and the cleaned HTML content simultaneously, skipping the double-hop latency. If you already have specific document identifiers, `get_contents` pulls down the cleaned text directly. This keeps your BigQuery and Vertex AI workflows supplied with fresh ground-truth data from the web.

Domain tracking and similarity mapping

`find_similar` identifies websites that share a conceptual footprint with your target URL. Enterprise agents use this to discover competitor sites or gather parallel research documents automatically. To keep your pipelines running smoothly, `get_api_usage` tracks your current crawl statistics and API consumption. This gives your system administrators real-time visibility into operational costs.

Setup guide

Set up Exa AI MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Exa AI tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Exa AI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Exa AI tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Exa AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Exa AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Exa AI MCP in Google ADK

Instantiate `McpToolset` using the Streamable HTTP parameters pointing to your Vinkius endpoint. Pass this toolset directly to your `LlmAgent` to let Gemini auto-discover the available search capabilities.

Yes, Google ADK supports an optional tool name filter during initialization. You can expose only `get_search_links` if you want to limit the agent to link discovery and prevent full page downloads.

The `get_contents` tool strips out bloated script tags and styling markup to deliver dense, readable text. This allows Gemini to analyze dozens of full-length articles simultaneously without hitting token limits.

You can run search queries, extract web data, and write the output directly to BigQuery using standard ADK tools. This lets you build agents that enrich internal database records with real-time web intelligence via the MCP Server.

Your search parameters and retrieved HTML payloads are processed in a secure, isolated sandbox. No data is cached on disk, preventing leaks of sensitive enterprise research or proprietary query strings from the MCP connection.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript