How to Use the Anthropic MCP in Google ADK

Q: How do I connect the Anthropic MCP Server to Google ADK?

Use McpToolset with the HTTP transport pointing to your Vinkius endpoint. Your Google ADK agent will instantly discover tools like createmessage and createbatch.

Q: Can Google ADK run async Anthropic batches?

Yes, your Google ADK agent can initiate batches with createbatch and track their progress using getbatch. This is perfect for processing large tables exported from BigQuery.

Q: How does Google ADK estimate Anthropic API costs?

The agent invokes estimatecost with your prompt's token count before sending it. This lets your Google ADK workflow manage budgets before committing to expensive Claude API calls.

Q: How do I limit which Anthropic tools Google ADK can access?

You can pass a filtered list of tool names to your McpToolset constructor. This restricts your Google ADK agent to specific actions like checkratelimits while blocking others from this MCP Server.

Feed BigQuery data directly into Claude models using an MCP Server with 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 Anthropic MCP to Google ADK

Create your Vinkius account to connect Anthropic 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 Anthropic with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process BigQuery pipelines with Google ADK and Claude

Your Google ADK agents can pull massive datasets from BigQuery and send them to Claude using `create_batch` for cheap, asynchronous processing. This lets you run heavy data analysis without blocking your main execution threads. Once the batch completes, your agent retrieves the structured data with `get_batch_results` and writes it back to your Google Cloud storage. You get the reasoning power of Anthropic combined with Google's data infrastructure.

Dynamic model selection for Google ADK agents

Let your Google ADK agent choose the best Claude model for the job by querying `list_models` at runtime. The agent checks technical parameters using `get_model_specs` to match the model to your data size. If the task requires a cheap, fast response, it triggers `create_message` on a lighter model. For heavy analytical tasks, it scales up to Claude's largest context window.

Cost control for Google ADK on Anthropic

Running enterprise agents on Google ADK can get incredibly expensive if left unchecked. This MCP Server gives your agent the ability to run `estimate_cost` before executing massive prompt batches. If the estimated cost exceeds your Google Cloud budget threshold, the agent can halt the operation or use `cancel_batch` to stop pending jobs. It keeps your enterprise AI spend fully predictable.

Setup guide

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

Use `McpToolset` with the HTTP transport pointing to your Vinkius endpoint. Your Google ADK agent will instantly discover tools like `create_message` and `create_batch`.

Yes, your Google ADK agent can initiate batches with `create_batch` and track their progress using `get_batch`. This is perfect for processing large tables exported from BigQuery.

The agent invokes `estimate_cost` with your prompt's token count before sending it. This lets your Google ADK workflow manage budgets before committing to expensive Claude API calls.

You can pass a filtered list of tool names to your `McpToolset` constructor. This restricts your Google ADK agent to specific actions like `check_rate_limits` while blocking others from this MCP Server.

All batch files and prompt contents are sent directly to Anthropic's secure endpoints. Vinkius hosts the server in a secure sandbox, ensuring your Google ADK data remains completely private.

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