DingTalk MCP for AI. Automate approvals, track attendance, and map departments.

Q: How do I find all departments using listalldepartments?

Running listalldepartments provides a complete, top-level list of every department ID in the organization. This is your starting point for mapping or querying other groups.

Q: Can I check an employee's profile using getuserinfo?

Yes, you must provide the user’s unique ID to getuserinfo. It pulls up their detailed contact and profile information instantly for verification.

Q: If I need to track a purchase, do I use createapprovalprocess?

Yes. You start by calling createapprovalprocess with the required details (like process code and user ID). This sets up the official workflow instance.

Q: I need to check if a department has sub-teams; what parameters should I use with listsubdepartments?

You pass the parent department's ID to listsubdepartments. This command maps out the full organizational depth under that specific unit, helping you pinpoint niche teams or regional offices. It’s essential for understanding complex reporting lines and ensuring your notifications go to the right group.

Q: If I want to check if a pending leave request was approved or rejected, which tool should I use: getapprovalinstance?

Use getapprovalinstance. You simply provide the process instance ID. The function returns the current status (pending, approved, rejected) along with who made the last decision and when. This is your quickest way to identify bottlenecks in any workflow.

Q: How do I use getattendancerecords to find all instances of late or early check-ins?

When calling getattendancerecords, you must specify the date range. The output includes a flag for normal vs. abnormal attendance. This allows HR teams to filter directly on discrepancies, skipping through clean data and focusing only on issues.

Q: I know the Department ID; how can I use listusersbydepartment to get a full roster of users?

Pass the department's unique ID into listusersbydepartment. The function returns names, IDs, and avatars for every user associated with that team. This is more efficient than listing all company users because you get exactly who belongs in that specific group.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

DingTalk MCP connects your agent directly into Alibaba’s B2B office platform. You gain instant access to core corporate functions—from mapping complex organizational charts and tracking who's where, to managing attendance records and automating approval requests.

Manage user profiles, send rich notifications, and process leave or reimbursement workflows all without opening the DingTalk app. It gives your agent a real set of tools for enterprise operations.

What your AI can do

Create approval process

Starts a new workflow instance for things like leave, reimbursement, or purchases by defining the required fields and process type.

Get approval instance

Retrieves the current status of an approval request, showing who reviewed it and what decisions were made.

Get attendance records

Pulls timestamps and checkout types to show employee attendance data for specific date ranges.

+ 7 more capabilities included

Map Organizational Structure

List and explore departments and sub-departments to understand the company's full reporting hierarchy.

Manage User Directory

Search for, retrieve details on, or list profiles of specific employees using their IDs.

Monitor Time and Attendance

Pull employee check-in/check-out records to verify timesheets, track late arrivals, or monitor overall attendance patterns.

Process Approvals

Initiate new approval workflows for things like leave requests or purchases, and check the current status of any running process.

Send Rich Notifications

Send formatted announcements, alerts, or detailed reports to multiple team members directly through DingTalk's messaging feed.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

DingTalk: 10 Enterprise Tools for Operations

These tools let you automate corporate functions like managing user profiles, running attendance reports, or starting formal approval workflows through conversation.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using DingTalk on Vinkius

Create Approval Process

Starts a new workflow instance for things like leave, reimbursement, or purchases by defining the required fields and process type.

Get Approval Instance

Retrieves the current status of an approval request, showing who reviewed it and...

Get Attendance Records

Pulls timestamps and checkout types to show employee attendance data for specific...

Get Department Info

Gets detailed information about a single department, useful for understanding its...

Get User Info

Looks up specific employee details using their unique user ID.

List All Departments

Provides a complete list of every top-level department in the entire company structure.

List Sub Departments

Lists all smaller teams that fall under a specific parent department.

List Users By Department

Retrieves the full list of users and their basic profile info within a designated...

Send Markdown Message

Sends highly formatted, structured text reports or alerts with titles and links to...

Send Work Notification

Sends a direct work notification message containing basic text or markdown details...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The DingTalk integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "dingtalk": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the DingTalk tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"dingtalk": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with DingTalk, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Tracking who was where and when used to take hours of cross-referencing.

Today, tracking attendance means pulling reports from the physical clock system, then exporting that data into a separate HR dashboard. You have to manually compare those timesheets against project schedules in a third system just to flag discrepancies or calculate PTO usage. It's clicking through tabs and copy-pasting dates until your eyes blur.

With this MCP, you ask your agent directly: 'Who was late last week?' The agent immediately uses `get_attendance_records` and returns the precise list of names and times right in the chat window. You get a clean, actionable report instantly.

Using DingTalk for Workflows and Approvals

You currently have to send an email request for time off, wait for a manager to manually review it in another system, and then follow up via chat to see if the approval went through. It's slow, fragmented, and requires three different systems just to confirm one status.

Now, you can use `create_approval_process` to kick off the request directly from your conversation. You don't need to leave the chat; your agent tracks the whole thing for you by querying the status with `get_approval_instance`. It works.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

DingTalk is Alibaba’s main platform for corporate communication and collaboration. Connecting it through an MCP means you can tell your AI client to perform complex office tasks using natural conversation, instead of needing to log into multiple dashboards. Your agent can pull user lists by department, map the company's reporting structure, or check if a leave request passed approval—all in one go.

You don't just get data; you trigger actions. For example, your agent handles checking timesheets and flagging late arrivals based on recorded attendance. Whether you’re an HR manager needing to monitor patterns or an operations leader tracking purchase approvals, this MCP gives your agent the necessary tools. Vinkius makes connecting this massive system simple, letting any compatible client access all these functions immediately.

Built · Hosted · Managed by Vinkius DingTalk MCP - Manage Corporate Workflows & Attendance

Server ID 019d842e-46c2-7153-afa9-1d5cfa8cea18

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

Stop manually checking timesheets. Instead, use get_attendance_records to ask your agent for an immediate report on who was late or absent between two dates.

Managing complex team communication is easier. Use send_markdown_message to send out structured reports—like quarterly results or policy changes—with professional formatting and links.

Don't get lost in the org chart. Running list_all_departments immediately gives you a clear, actionable map of every department and its ID for future queries.

Skip the paperwork trail. If an employee needs time off, your agent can use create_approval_process to start the request instantly, which you then track with get_approval_instance.

You always know who's on the team. By calling list_users_by_department, you get a current roster of user IDs and names for any department in seconds.

See it in action

01 01

The Payroll Audit

A manager needs to audit attendance records for three employees across two weeks. They ask their agent, who uses get_attendance_records and then compiles a clean report showing all late arrivals, saving hours of spreadsheet work.

02 02

The Restructuring Announcement

HR needs to announce new reporting lines. The agent first calls list_all_departments and then uses the department IDs to send a formatted message via send_markdown_message, ensuring everyone gets the update.

03 03

The Expense Check

An employee submits an expense report. Instead of emailing a manager, the agent automatically calls create_approval_process for reimbursement, and the manager uses get_approval_instance to review its status immediately.

04 04

Finding Team Contacts

A developer needs contact info for the entire Product Marketing team. The agent first runs list_sub_departments to find the right group, then uses list_users_by_department to pull all necessary user IDs and names.

The honest tradeoffs

Trying to send a simple text message.

Anti-pattern

The user thinks they just need the basic notification function, so they use send_work_notification but don't include formatting or links. The resulting message looks plain and unprofessional.

The Fix

For any official announcement or report, use send_markdown_message. This tool lets you structure content with titles, bold text, and clickable links, making the message look professional.

Not knowing which department to query first.

Anti-pattern

A user tries to call list_users_by_department without a valid ID or assumes the root company directory is '1'. The tool fails because it needs precise context.

The Fix

Always start by running list_all_departments. This gives you the definitive list of department IDs, which you can then pass to list_users_by_department.

Assuming an approval process exists.

Anti-pattern

A user tries to check a status using get_approval_instance without knowing the specific process ID. The agent returns an error, and the conversation stalls.

The Fix

Before checking status, you must first use create_approval_process (if applicable) or get the ID from another source to ensure the instance exists.

When It Fits, When It Doesn't

Use this MCP if your workflow involves corporate data: user directories, organizational hierarchy, attendance records, or formal approvals. Specifically, if you need to check a timesheet using get_attendance_records or initiate an official leave request with create_approval_process, this is the tool. Don't use it if your goal is simple personal messaging; for that, a general chat platform API might suffice. Also, don't try to manage budget calculations here—this MCP handles people and processes, not financial math.

Questions you might have

How do I find all departments using list_all_departments? +

Running list_all_departments provides a complete, top-level list of every department ID in the organization. This is your starting point for mapping or querying other groups.

Can I check an employee's profile using get_user_info? +

Yes, you must provide the user’s unique ID to get_user_info. It pulls up their detailed contact and profile information instantly for verification.

What should I use to send a formatted announcement? Is it send_work_notification? +

For anything that needs structure—like an alert with bold text or clickable links—you must use send_markdown_message. This ensures the message looks professional and organized.

If I need to track a purchase, do I use create_approval_process? +

Yes. You start by calling create_approval_process with the required details (like process code and user ID). This sets up the official workflow instance.

I need to check if a department has sub-teams; what parameters should I use with `list_sub_departments`? +

You pass the parent department's ID to list_sub_departments. This command maps out the full organizational depth under that specific unit, helping you pinpoint niche teams or regional offices.
It’s essential for understanding complex reporting lines and ensuring your notifications go to the right group.

If I want to check if a pending leave request was approved or rejected, which tool should I use: `get_approval_instance`? +

Use get_approval_instance. You simply provide the process instance ID. The function returns the current status (pending, approved, rejected) along with who made the last decision and when.
This is your quickest way to identify bottlenecks in any workflow.

How do I use `get_attendance_records` to find all instances of late or early check-ins? +

When calling get_attendance_records, you must specify the date range. The output includes a flag for normal vs. abnormal attendance.
This allows HR teams to filter directly on discrepancies, skipping through clean data and focusing only on issues.

I know the Department ID; how can I use `list_users_by_department` to get a full roster of users? +

Pass the department's unique ID into list_users_by_department. The function returns names, IDs, and avatars for every user associated with that team.
This is more efficient than listing all company users because you get exactly who belongs in that specific group.

How do I get my DingTalk App Key and App Secret? +

Log in to the DingTalk Developer Console, create an Internal Enterprise Application, then navigate to App Information > Credentials to find your AppKey and AppSecret. Make sure your application has the required API permissions (User Management, Department Management, Attendance, Approval) before using these tools.

Can I send messages to external contacts or only internal employees? +

This MCP server uses Internal Enterprise Application authentication, which means it can only send messages to users within your organization's DingTalk tenant. For external contacts or customer notifications, you would need a different DingTalk application type with extended permissions. All user IDs must belong to employees in your enterprise directory.

How does the attendance tracking work? What data can I retrieve? +

The attendance tool retrieves check-in/check-out records from DingTalk's attendance system. For each record, you get the user ID, timestamp, checkout type (上班签到=check-in, 下班签退=check-out), location information, and whether the attendance was normal or abnormal (late, early leave, missing punch). Date ranges are specified in YYYY-MM-DD format. This data integrates with DingTalk's physical attendance devices and mobile check-in features.

Connect to your AI in seconds.

Create approval process

Get approval instance

Get attendance records

DingTalk: 10 Enterprise Tools for Operations

Make your AI actually useful.

Create Approval Process

Get Approval Instance

Get Attendance Records

Get Department Info

Get User Info

List All Departments

List Sub Departments

List Users By Department

Send Markdown Message

Send Work Notification

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Tracking who was where and when used to take hours of cross-referencing.

Using DingTalk for Workflows and Approvals

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

The Payroll Audit

The Restructuring Announcement

The Expense Check

Finding Team Contacts

The honest tradeoffs

Trying to send a simple text message.

Not knowing which department to query first.

Assuming an approval process exists.

When It Fits, When It Doesn't

Questions you might have