How to Use the GroundX MCP in Google ADK

Q: How does GroundX integrate with Google ADK long-context models?

Your Gemini agent uses searchcontent to pull relevant document chunks first. It then packs these high-quality results into its large context window to perform reasoning without cluttering the prompt with irrelevant noise.

Q: Can I limit the GroundX tools exposed to my Google ADK agent?

Yes, you use the toolnames filter when initializing your McpToolset. This lets you hide administrative tools like creategroup and only expose searchdocuments to customer-facing agents.

Q: How does Google ADK handle GroundX ingestion delays?

Your agent initiates ingestion with ingestdocuments and then polls getingeststatus. Because the ADK supports async execution, your agent can run other tasks while waiting for the indexing to complete.

Connect the GroundX MCP Server to your Google ADK to run deep search queries across massive enterprise documents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GroundX MCP to Google ADK

Create your Vinkius account to connect GroundX 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 GroundX with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise Ingestion for Google ADK

GroundX provides the `ingest_documents` tool to feed raw documents directly into your Gemini agent workflows. This setup lets your long-context model scan entire databases by passing retrieved chunks straight into the 1M-token window. You can also trigger `ingest_website` to crawl public documentation on demand. The Google ADK toolset handles the transport layer, letting your agent monitor the pipeline via `get_ingest_status` without manual polling code.

Semantic Search across BigQuery and GroundX

This MCP Server allows Gemini models to combine structured BigQuery data with unstructured content via `search_content`. Your agent queries both sources simultaneously to build a complete context package for complex reasoning. Using `search_documents`, the agent filters results by specific metadata fields. This ensures that the Gemini model only receives highly relevant context, reducing token costs even when dealing with massive file systems.

Multi-Tenant Data Control in Google Cloud

GroundX structures data using `create_bucket` and `create_group` to keep enterprise clients separated. Your Gemini agent checks these boundaries using `list_buckets` and `list_groups` before running any search query. The ADK handles the connection to these tools using standard HTTP transport. You can restrict access to this MCP Server so that specific agent instances only see the `list_workflows` tool, keeping administration tasks secure.

Setup guide

Set up GroundX 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 GroundX 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="GroundX_agent",
    model="gemini-2.0-flash",
    instruction="You have access to GroundX 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 GroundX. 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 GroundX 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 GroundX MCP in Google ADK

Your Gemini agent uses `search_content` to pull relevant document chunks first. It then packs these high-quality results into its large context window to perform reasoning without cluttering the prompt with irrelevant noise.

Yes, you use the `tool_names` filter when initializing your `McpToolset`. This lets you hide administrative tools like `create_group` and only expose `search_documents` to customer-facing agents.

Your agent initiates ingestion with `ingest_documents` and then polls `get_ingest_status`. Because the ADK supports async execution, your agent can run other tasks while waiting for the indexing to complete.

You set your token in the Vinkius console, which provides a single secure endpoint URL. You pass this URL directly to `StreamableHttpServerParameters` when setting up your toolset.

All crawled web content, PDFs, and index metadata are stored in secure, isolated buckets. The Vinkius MCP Server sandbox ensures your data never touches external networks, maintaining strict compliance with Google Cloud security policies.

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