How to Use the DingTalk MCP in Google ADK

Q: How do I register the DingTalk MCP Server within a Google ADK agent?

Instantiate McpToolset with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into the tools list of your LlmAgent to let Gemini discover the endpoints.

Q: Can I restrict which DingTalk tools my Google ADK MCP agent can access?

Yes. Use the toolnames parameter in the McpToolset constructor to limit exposure, ensuring the agent only runs specific tools like sendworknotification while blocking approval actions.

Q: Can I sync my Google Cloud directory with DingTalk departments?

You can write an agent that calls listusersbydepartment and getdepartmentinfo to pull your current organization tree, then matches it against your IAM directory.

Analyze BigQuery data and trigger DingTalk workflows using Google ADK and Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DingTalk MCP to Google ADK

Create your Vinkius account to connect DingTalk 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 DingTalk with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise workflow automation with Google ADK

Gemini's long-context window allows your agent to digest massive operational reports from BigQuery. Once the analysis is complete, the agent can use this MCP Server to trigger actions directly in your office suite. It executes `create_approval_process` to submit purchase orders or leave requests based on your cloud data. The agent keeps track of these tasks without losing state. It polls `get_approval_instance` to verify if the business workflow is complete, feeding the status back into your Vertex AI pipeline.

Real-time HR insights and attendance auditing

Your Google ADK agent can process thousands of employee records simultaneously. By calling `get_attendance_records`, the agent pulls raw check-in data and compares it against historical schedules stored in your Google Cloud databases. This allows you to spot patterns of late arrivals or location discrepancies instantly. The agent can then pull detailed profiles using `get_user_info` to compile a detailed operational report for HR managers.

Targeted department communications from Gemini agents

Sending bulk alerts is noisy and inefficient. Your agent can use this MCP toolset to query `list_all_departments` and `list_sub_departments` to understand the exact corporate structure before sending a single message. This ensures communications only go to the relevant team divisions. When the target group is identified, the agent calls `send_markdown_message` or `send_work_notification` to dispatch formatted alerts. Because Gemini understands complex markdown, your notifications will look clean and professional on employee mobile screens.

Setup guide

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

Instantiate `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset into the `tools` list of your `LlmAgent` to let Gemini discover the endpoints.

Yes. Use the `tool_names` parameter in the `McpToolset` constructor to limit exposure, ensuring the agent only runs specific tools like `send_work_notification` while blocking approval actions.

Gemini can ingest months of attendance history retrieved via `get_attendance_records` in a single prompt. It analyzes these patterns alongside your BigQuery warehouse data to find operational bottlenecks.

You can write an agent that calls `list_users_by_department` and `get_department_info` to pull your current organization tree, then matches it against your IAM directory.

Yes. The connection uses an ephemeral V8 sandbox that processes `get_user_info` queries on the fly. No user profile data or DingTalk credentials are cached or stored on Vinkius servers.

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