How to Use the watsonx Discovery MCP in Google ADK

Q: Can I list all available data collections using watsonx Discovery and the Google ADK?

Yes. You use the listdiscoverycollections tool to get a complete inventory of every collection in your project space, helping structure agent actions.

Q: Does watsonx Discovery support entity extraction with the Google ADK?

It does. The listavailableenrichments method shows which NLP models are applied to documents, including Entities and Sentiment. Your agent can rely on this enriched data.

Q: What kind of queries can I run with watsonx Discovery and the Google ADK?

You perform natural language or DQL queries using querydiscoverycontent. This allows your agent to analyze complex, unstructured data just like a human researcher would.

Q: What kind of metadata does watsonx Discovery handle when using the Google ADK?

It manages document and system configuration settings. The getdocumentdetails tool helps your agent retrieve specific metadata, confirming the status of indexed documents.

Connect watsonx Discovery search capabilities to BigQuery and Vertex AI using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect watsonx Discovery MCP to Google ADK

Create your Vinkius account to connect watsonx Discovery 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 watsonx Discovery with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Running Natural Language Queries

To query data, you pass a collection ID and the desired query text. This executes `query_discovery_content`, letting your agent run deep search and analysis powered by watsonx Discovery. It's built for enterprise agents that need to act on massive amounts of indexed corporate information. This mechanism allows your agent to synthesize answers from multiple data sources, far beyond what a simple API call could achieve.

Inventorying Data Assets

The `list_discovery_collections` tool provides an immediate listing of all available data collections in the project. Your agent uses this to map out its search scope before running any queries. Furthermore, if you need a file-level view, `list_collection_documents` gives you every document indexed within a specific collection.

Validating System Components

`get_component_settings` reads the health and configuration status for any project component. Your agent can use this to confirm that all required services are online before executing critical search tasks. You can combine this check with `get_document_details` to verify specific file statuses, ensuring your workflow is reliable from start to finish.

Setup guide

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

The Google ADK lets you build agents that natively call MCP tools like `query_discovery_content`. It's ideal when your existing data lives in BigQuery and needs deep search capabilities.

Yes. You use the `list_discovery_collections` tool to get a complete inventory of every collection in your project space, helping structure agent actions.

It does. The `list_available_enrichments` method shows which NLP models are applied to documents, including Entities and Sentiment. Your agent can rely on this enriched data.

You perform natural language or DQL queries using `query_discovery_content`. This allows your agent to analyze complex, unstructured data just like a human researcher would.

It manages document and system configuration settings. The `get_document_details` tool helps your agent retrieve specific metadata, confirming the status of indexed documents.

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