How to Use the Jina AI (Search Foundation & LLM Grounding) MCP in Google ADK

Q: How do I add Jina AI (Search Foundation & LLM Grounding) to a Google ADK agent?

Use the McpToolset class to define your server parameters. Once you pass this toolset to your LlmAgent, it exposes the Jina AI tools alongside your existing Google Cloud connections.

Q: Does Jina AI (Search Foundation & LLM Grounding) support the long-context features in Google ADK?

Absolutely. You can use readurlcontent to pull large amounts of text into your agent's context. Because the server returns clean markdown, it is easier for Gemini to reason over the entire document.

Q: How do I restrict tool access in Google ADK using Jina AI (Search Foundation & LLM Grounding)?

You can use the toolnames filter within the McpToolset constructor. This lets you expose only the specific tools your agent needs, keeping your interface clean.

Connect Google ADK to the web. Get semantic search and document reranking for your enterprise agents.

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 (Search Foundation & LLM Grounding) MCP to Google ADK

Create your Vinkius account to connect Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise web search for Google ADK

Bring live internet data into your Google Cloud workflows. The `search_web_jina` tool fetches context-rich results that your Gemini-powered agents can act on immediately. It handles the heavy lifting of parsing search results. You get clean, usable content that integrates directly into your agent's reasoning loop.

Refined document retrieval for Google ADK

Don't overwhelm your model with irrelevant noise. Use `rerank_documents` to filter your search results based on the specific intent of your user's query. This tool ensures the documents passed to your agent are ranked by semantic relevance. It keeps your RAG pipeline tight and prevents the agent from wasting tokens on poor matches.

Versatile text processing for Google ADK

Use `classify_texts` to categorize incoming data streams before they hit your database. It's a quick way to tag content for your downstream BigQuery analytics. When you need to process raw text, `segment_content` ensures your chunks are semantically sound. This keeps your data organized and ready for the 1M+ token context windows available in Gemini.

Setup guide

Set up Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) MCP in Google ADK

Use the `McpToolset` class to define your server parameters. Once you pass this toolset to your `LlmAgent`, it exposes the Jina AI tools alongside your existing Google Cloud connections.

Absolutely. You can use `read_url_content` to pull large amounts of text into your agent's context. Because the server returns clean markdown, it is easier for Gemini to reason over the entire document.

You can use the tool_names filter within the `McpToolset` constructor. This lets you expose only the specific tools your agent needs, keeping your interface clean.

The server supports both Stdio and HTTP transports. You choose the one that fits your deployment architecture in Google Cloud.

The server processes your data in an ephemeral sandbox. It does not persist your search queries or the content it scrapes, ensuring your internal data remains contained within your own infrastructure.

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