How to Use the IBM watsonx MCP in Google ADK

Q: Can I filter tools when using IBM watsonx with Google ADK?

You can use the toolnames filter in your McpToolset setup. This restricts the agent to only the tools you explicitly permit, like generatetext or listmodels.

Q: Is IBM watsonx compatible with Google ADK for long-context tasks?

Yes. You can pass large chunks of data to generatetext or generatechat. The server handles the request transmission to the watsonx backend.

Integrate IBM watsonx with the Google ADK to bridge your enterprise data and foundation model reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBM watsonx MCP to Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct model orchestration for Google ADK

The `McpToolset` lets your Google ADK agent reach into watsonx to call `list_models` and `get_model_details`. You define the server parameters once, and the agent treats the tools as native functions. This is for developers who need to swap models dynamically. Your agent can query the available models and adjust its strategy based on the specific family or state returned by the server.

Unified project and prompt management

Your agent can now list projects with `list_projects` and manage templates using `list_prompts` or `create_prompt`. This keeps your agent's configuration synchronized with your account workspace. It removes the need for manual context switching. The agent fetches the right project context, ensuring all subsequent generation calls use the correct environment settings.

Scalable chat and text generation

Use `generate_text` and `generate_chat` to handle complex reasoning tasks. By connecting this MCP Server, your agent gains access to powerful foundation models without needing custom API wrappers. It fits into your existing Google Cloud infrastructure. You maintain standard operational patterns while extending your agent's capabilities with watsonx-specific logic.

Setup guide

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

It provides a direct conduit for model calls. By using the server, you reduce the boilerplate code required to connect your agent to external foundation models.

You can use the tool_names filter in your `McpToolset` setup. This restricts the agent to only the tools you explicitly permit, like `generate_text` or `list_models`.

Yes. You can pass large chunks of data to `generate_text` or `generate_chat`. The server handles the request transmission to the watsonx backend.

Vinkius provides a single endpoint token. You pass this to the server parameters, and it handles the handshake with the watsonx infrastructure.

The server acts as a pass-through for model interaction. Your input text is processed by watsonx and the results are returned to the agent, with no persistent storage on the server itself.

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