How to Use the Dify.AI SDK MCP in Google ADK

Q: How do I connect the Dify.AI SDK to my Google ADK agent?

Install the package using pip and instantiate McpToolset with your Vinkius server URL. This registers the MCP Server so you can pass this toolset into your LlmAgent constructor to expose all 14 tools to Gemini.

Q: Can I restrict which Dify.AI SDK tools Google ADK can access?

Yes. Use the toolnames filter parameter in the StreamableHttpServerParameters configuration. This lets you expose only specific tools like runworkflow while keeping administrative tools hidden from the agent.

Q: How do I get metadata about my Dify applications?

The getappmeta tool retrieves the configuration details of your target application. Your agent uses this to understand which features, like speech-to-text or file uploads, are enabled.

Connect Gemini models to your Dify workflows using Google ADK to run complex enterprise pipelines with BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dify.AI SDK MCP to Google ADK

Create your Vinkius account to connect Dify.AI SDK 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.AI SDK with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Dify workflows with BigQuery data

The `run_workflow` tool triggers structured Dify automation directly from your enterprise data pipelines. Your Gemini agent queries BigQuery, structures the results, and passes them as parameters to the workflow. This connects your analytical database directly to external AI application engines. Execution parameters are parsed dynamically using `get_workflow_parameters` before the call is made. The agent validates that the schema matches what Dify expects, preventing failed runs. You get back structured JSON outputs that your Google ADK agent can write back to your cloud storage.

Analyze massive chat histories with Google ADK

The `get_conversation_messages` tool pulls historical chat logs directly into Gemini's 1-million-token context window. By integrating this MCP Server, your agent reads the entire history to maintain perfect continuity. This allows for deep reasoning across months of customer interactions. You can manage these sessions at scale using `get_conversations` to list active threads. If a thread requires cleanup, the agent invokes `delete_conversation` based on your retention policies. All of this happens programmatically within your Google Cloud security boundary.

Multi-modal analysis via Cloud Storage

The `upload_file` tool sends document and image URLs directly to Dify for processing. Your Google ADK agent grabs files from Google Cloud Storage buckets and hands them to this MCP Server tool before starting a chat. This enables Dify's vision and document models to analyze your enterprise assets. Once the file is processed, the agent starts a session using `chat_message`. If the user asks for follow-up resources, `get_suggested_questions` predicts the next logical steps in the conversation. This creates a fully automated, interactive support loop.

Setup guide

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

Install the package using pip and instantiate `McpToolset` with your Vinkius server URL. This registers the MCP Server so you can pass this toolset into your `LlmAgent` constructor to expose all 14 tools to Gemini.

Yes. Use the `tool_names` filter parameter in the `StreamableHttpServerParameters` configuration. This lets you expose only specific tools like `run_workflow` while keeping administrative tools hidden from the agent.

Yes. This MCP Server supports both connection methods. For cloud deployments on Cloud Run, the streamable HTTP transport is the recommended choice.

The `get_app_meta` tool retrieves the configuration details of your target application. Your agent uses this to understand which features, like speech-to-text or file uploads, are enabled.

Your raw workflow inputs and parameter schemas are processed inside ephemeral, zero-trust V8 isolates. Vinkius does not log the payloads passing through the server. All communication between Gemini and Dify is encrypted using TLS 1.3.

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