How to Use the DeepSeek MCP in Google ADK

Q: How do I connect this MCP Server to my google-adk project?

Install google-adk and use the McpToolset class with your Vinkius HTTP URL. Pass the toolset directly into your LlmAgent tool list.

Q: Can google-adk agents use this MCP Server for heavy reasoning?

Yes. Your agent will automatically select the deepreasoning tool when it encounters a complex logic problem that requires structured thinking.

Q: Can I limit which DeepSeek tools are exposed to google-adk?

Yes, you can use the optional toolnames filter in your McpToolset configuration to expose only specific tools like chatcompletion.

Connect DeepSeek models to your Google ADK enterprise pipelines and BigQuery datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepSeek MCP to Google ADK

Create your Vinkius account to connect DeepSeek 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 DeepSeek with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run DeepSeek reasoning alongside BigQuery data

The `deep_reasoning` tool brings deep logical analysis to your enterprise datasets. Your Google ADK agent pulls raw tables from BigQuery and feeds them directly into DeepSeek to find hidden patterns. You use `chat_completion` to generate structured summaries of your cloud data. This setup lets Gemini handle the massive 1M+ token context while DeepSeek tackles the heavy logic.

Manage active models inside Google ADK

The `list_models` tool fetches all available DeepSeek models so your enterprise agent can select the right one for the job. You don't have to hardcode model names into your Vertex AI setup. Your agent queries `get_model_details` to inspect model metadata dynamically at runtime. This allows your system to adapt when new open-weight models are released.

Audit DeepSeek MCP Server operations

The `list_request_history` tool retrieves previous API calls to help you monitor what your enterprise agents are doing. This keeps your GCP compliance logs complete and accurate. You can also call `list_api_tokens` to inspect which credentials your agents are using. It gives you full visibility into the system's external footprint.

Setup guide

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

Install `google-adk` and use the `McpToolset` class with your Vinkius HTTP URL. Pass the toolset directly into your `LlmAgent` tool list.

Yes. Your agent will automatically select the `deep_reasoning` tool when it encounters a complex logic problem that requires structured thinking.

Yes, you can use the optional `tool_names` filter in your `McpToolset` configuration to expose only specific tools like `chat_completion`.

This MCP Server connection supports both standard Stdio and Streamable HTTP transports, making it easy to deploy inside Google Cloud Run or GKE.

Vinkius runs every request inside an isolated, zero-trust V8 sandbox. Your request history and prompt tokens are never stored on Google's infrastructure or used for model training.

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