How to Use the Dify MCP in Google ADK

Q: How do I register the Dify MCP Server inside a Google ADK agent?

Initialize McpToolset with your Vinkius HTTP transport URL. Pass this toolset into the tools list when creating your LlmAgent in Python.

Q: Can Google ADK agents upload files directly to my Dify workspace?

Yes, the agent invokes uploadfile to send assets straight to your workspace. This makes the files instantly queryable by your Gemini-powered agent.

Q: How does Google ADK manage conversation histories stored in Dify?

Your agent uses listconversations and listmessages to pull historical threads. This MCP toolset lets you feed clean, structured context into Gemini's long-context window.

Q: Does this integration support feedback logging?

Yes, the agent calls the feedback tool to submit user ratings for specific messages. This helps track agent performance directly inside your dashboard.

Connect Google ADK to Dify to run long-context Gemini workflows with direct access to application parameters and chat history.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dify MCP to Google ADK

Create your Vinkius account to connect Dify 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 Dify with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Dify chats into Google ADK pipelines

Your Google ADK agents can now route user queries directly to Dify using the `chat` tool. This lets you combine Gemini's massive context window with structured workflow setups in Python. To close the loop, the agent uses `feedback` to log user ratings back to your system. Running optimization pipelines becomes effortless without custom API plumbing.

Audit system parameters using this MCP Server

Enterprise agents on Google ADK often need to check configurations before acting. By calling `get_parameters`, your agent pulls live system prompts and model definitions directly from your workspace. This runtime metadata allows your Gemini models to adjust their reasoning paths on the fly. You don't have to hardcode prompts into your Google Cloud deployment.

Synchronize massive histories inside Google ADK

Keep your Gemini model up to date by fetching full chat histories with `list_conversations` and `list_messages`. This ensures your agent has the complete background before generating a response. When handling documents, the agent uses `upload_file` to push files to the correct workspace. Your BigQuery and Vertex integrations stay perfectly aligned with your active chat sessions.

Setup guide

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

Initialize `McpToolset` with your Vinkius HTTP transport URL. Pass this toolset into the `tools` list when creating your `LlmAgent` in Python.

Yes, the agent invokes `upload_file` to send assets straight to your workspace. This makes the files instantly queryable by your Gemini-powered agent.

Your agent uses `list_conversations` and `list_messages` to pull historical threads. This MCP toolset lets you feed clean, structured context into Gemini's long-context window.

Yes, the agent calls the `feedback` tool to submit user ratings for specific messages. This helps track agent performance directly inside your dashboard.

Yes, all file uploads, chat logs, and app parameters are handled inside ephemeral, single-tenant V8 isolates. The MCP transport secures your credentials and ensures no data is written to persistent third-party storage.

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