How to Use the Jina AI MCP in Google ADK

Q: Can I limit which Jina AI tools my Google ADK agent can see?

Yes, you can use the optional toolnames filter in your McpToolset configuration. This lets you expose only searchweb or readurl if you want to restrict agent capabilities.

Give your Google ADK agents the ability to search, scrape, and verify live web data across millions of context tokens.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jina AI MCP to Google ADK

Create your Vinkius account to connect Jina 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 Jina AI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground Gemini reasoning with an MCP Server

Your agent calls `search_web` and `check_fact` to ground Gemini reasoning with verified facts before saving data to BigQuery. This ensures your enterprise workflows are backed by real-time, checked data. Because Gemini models handle massive token windows, you can pull entire articles. Use `read_url` to grab clean markdown, ensuring your enterprise agent is not reading useless HTML boilerplate.

Clean and tokenize web data for Google ADK

Your agent uses `tokenize_text` to count tokens of scraped web content before sending payloads to Vertex AI. This helps you monitor usage and keep your cloud costs predictable. When your Google ADK agent gets raw pages via `read_url`, it cleans them instantly. You get the exact text you need without any of the web junk.

Rerank documents for better retrieval

Your agent uses `rerank_documents` to sort search results, ensuring Gemini only processes the most relevant context. This prevents long-context models from losing focus on middle-ground data. If you need to store these results, `get_embeddings` converts the sorted text into vectors. Your Google ADK agent can then write them straight to your enterprise database using our MCP integration.

Setup guide

Set up Jina 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 Jina 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="Jina AI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Jina 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 Jina 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 Jina 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 Jina AI MCP in Google ADK

Use pip install google-adk to set up the framework. Then, define an McpToolset with your Vinkius HTTP URL and pass it to the tools list of your LlmAgent.

The Google ADK toolset configuration supports both Stdio and HTTP transport protocols. For cloud-deployed enterprise agents, the streamable HTTP setup is highly recommended.

Yes, you can use the optional tool_names filter in your McpToolset configuration. This lets you expose only search_web or read_url if you want to restrict agent capabilities.

Vinkius manages all authentication behind the scenes. You only need a single endpoint token from your Vinkius dashboard to connect your agent to all six tools.

Vinkius executes everything inside an ephemeral, zero-trust V8 isolate sandbox. Your raw search queries, scraped text, embeddings, tokens, and target URLs are processed strictly in memory and destroyed instantly after the MCP server execution loop finishes.

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