Netease Yunxin MCP for AI. Automate Group Moderation and Messaging Flow

Q: What is the difference between sendp2pmessage and sendbatchmessage?

Use sendp2pmessage for a one-to-one private chat. Use sendbatchmessage when you need to send the exact same message content out to many different users at once.

Q: How do I manage team members using addteammember?

You ask your agent to run addteammember, specifying the target team ID and the user's unique account ID. The agent handles the join action for you.

Q: If my user token expires, how does the refreshusertoken tool help me maintain connectivity?

The refreshusertoken tool automatically retrieves and updates your IM access credentials. It validates your existing connection without requiring you to re-authenticate or manually input new security keys. This keeps your agent connected and ready for real-time chat operations.

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.

Netease Yunxin / 网易云信 manages large-scale real-time chat and messaging infrastructure. Use it with your AI client to create IM accounts, manage user groups, send direct or bulk messages, and audit message histories—all without touching a dashboard.

It handles complex communication tasks through simple conversational commands.

What your AI can do

Add team member

Adds a specific user to an existing chat team or group.

Create account

Creates and initializes a new IM account for a user.

Create team

Establishes an entirely new chat group or team structure.

+ 7 more capabilities included

Create User Accounts

The agent creates new IM accounts, managing the initial setup of user identities.

Modify Account Details

You can update an existing account's details or refresh its security token to keep it active.

Build and Manage Groups

The agent creates multi-user teams, adding members and removing users as needed for moderation.

Send Targeted Messages

It sends private one-on-one messages or executes bulk messaging to entire user lists.

Review Communication History

You retrieve complete chat logs and group metadata for auditing purposes over specific time ranges.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Netease Yunxin / 网易云信: 10 Tools for Comms Ops

Use these tools to create users, manage chat groups, send messages in bulk, and retrieve detailed communication logs via your AI client.

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 Netease Yunxin / 网易云信 on Vinkius

Add Team Member

Adds a specific user to an existing chat team or group.

Create Account

Creates and initializes a new IM account for a user.

Create Team

Establishes an entirely new chat group or team structure.

Get Session History

Retrieves and reads the full chat log between two users over a defined time range.

Get Team Detail

Pulls current metadata about an existing team, including its member list and...

Kick Team Member

Removes a specified user from a chat group or team.

Refresh User Token

Updates an IM account's token to prevent connection failures due to expiry.

Send Batch Message

Sends the exact same message content to multiple users simultaneously.

Send P2p Message

Delivers a direct, private message between two specified users.

Update Account

Changes specific details (like display name) for an existing IM account.

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 Netease Yunxin 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": {
  "netease-yunxin": {
    "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 Netease Yunxin 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:

"netease-yunxin": {
  "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 Netease Yunxin / 网易云信, 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 Netease Yunxin / 网易云信. 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.

Managing group membership shouldn't feel like a database query.

Right now, if you need to know who belongs in a project team, you have to log into the chat platform and click through multiple member lists. If someone leaves or joins, you're stuck clicking 'Add Member' or 'Remove User,' often requiring manual verification against an HR sheet.

With this MCP server, your agent handles it all. You just prompt: 'Can you add John Doe to Project Gamma?' The agent runs the necessary tools—like `add_team_member`—and confirms the change immediately. It’s instant group administration.

Netease Yunxin / 网易云信 MCP Server: Control the entire user lifecycle.

The biggest time sinks disappear. You don't manually update tokens, you don't run separate scripts for account creation, and you never have to switch between a chat UI and an identity management dashboard again.

This single connection lets your agent manage the entire communications stack—from initial user setup with `create_account` all the way through message auditing with `get_session_history`. It's one source of truth for all things messaging.

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

This server connects your AI client directly to Netease Yunxin, one of China's massive real-time communication platforms. It gives your agent full operational control over chat infrastructure—you can manage user accounts, moderate groups, and audit message history without ever touching a dashboard or running manual commands. If your job involves automated support, managing large user bases, or tracking complex communications flow, this is what you need.

Account Setup and Maintenance

Your agent handles the full lifecycle of an IM account. You can use create_account to spin up entirely new user identities from scratch. Once an account exists, you'll often need to make tweaks; that's where update_account comes in. It lets your client change details like a display name on an existing profile.

Critically, connections expire, so you can use refresh_user_token to keep any IM account active and prevent connection failures due to token expiry.

Group Creation and Moderation

Building teams is straightforward. You'll start by calling create_team to establish an entirely new chat group structure. Once the team exists, you control who's in it. Use add_team_member to bring a specific user into the existing group roster. When someone needs to be cut loose or leaves the project, you don't have to manually remove them; simply call kick_team_member.

To see exactly who’s in the group and what its current rules are, your agent pulls all that data using get_team_detail.

Sending Targeted Messages

Sending messages is done with precision. If you need to talk to one person privately—a direct chat—you use send_p2p_message. But if you're sending out an alert or a general announcement, you don't want to repeat the message hundreds of times. Instead, your client uses send_batch_message, which fires off the exact same content simultaneously to multiple users across different lists.

Reviewing Communication History and Metadata

For auditing purposes, you have full access to chat logs. You can retrieve complete conversation histories between any two people by calling get_session_history over a specific time range. This is essential for compliance or debugging. Furthermore, when you need context about the groups themselves—the current member list, group settings, etc.—you pull all that structural data with get_team_detail.

You're running a complete communications ops team through simple conversational commands. Your agent handles every step: setting up accounts, managing memberships, sending messages one-by-one or in bulk, and pulling detailed historical logs for review.

Built · Hosted · Managed by Vinkius Netease Yunxin MCP Server - Manage Chat & Accounts

Server ID 019d84a2-57fe-71b0-9598-5933c33e1822

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Who is this actually for?

This is for the support engineer who needs to audit chat logs across hundreds of users. It’s for community managers tired of manually moderating large groups. If your workflow relies on high-volume, real-time user communication, you need this.

Support Engineer

They use get_session_history and get_team_detail to quickly pull up specific customer chat logs for ticket resolution, bypassing the manual UI search.

Community Manager

They run send_batch_message or add_team_member to coordinate large community events, ensuring everyone in a group gets an announcement instantly.

DevOps Engineer

They use refresh_user_token and update_account as part of CI/CD scripts or automated maintenance flows, keeping the communication stack live.

What Changes When You Connect

Stop manually tracking group rosters. Use get_team_detail to instantly pull a team's current membership list, which is better than checking the UI tab by tab.

Handle mass communication without writing scripts. Just tell your agent to 'send an alert to all marketing users,' and it runs send_batch_message for you.

Eliminate account setup friction. Instead of a developer running a separate registration script, just ask your agent to create_account, and the user is ready to go.

Audit conversations in seconds. Need to know what was said last week? Running get_session_history pulls complete logs between any two users based on dates you provide.

Maintain connection integrity automatically. Use refresh_user_token so your agent doesn't fail mid-task because a user token expired overnight.

See it in action

01 01

New Employee Onboarding

An HR manager needs to get a new hire, 'jane', set up in the system. They ask their agent: 'Create IM account for jane and add her to the #marketing team.' The agent runs create_account then add_team_member, completing the process in two steps.

02 02

Crisis Communications

A company needs to send an urgent service update to 50,000 subscribers. Instead of logging into a separate broadcast system, they instruct their agent to run send_batch_message using the target list.

03 03

Investigating User Behavior

A support team needs to check if a user complained about a specific feature last month. They ask their agent to use get_session_history, providing the user's ID and the date range, and the logs are returned immediately.

04 04

Team Restructuring

The project scope changes, and 'user_x' needs to move from the 'Alpha' team to the 'Beta' team. The agent runs kick_team_member for Alpha and then add_team_member for Beta.

The honest tradeoffs

Trying to check history manually

Anti-pattern

Logging into the platform, navigating to User A's chat with User B, scrolling back months of conversation, and trying to copy relevant timestamps.

The Fix

Just tell your agent: 'Get the session history for users A and B from June 1st to June 30th.' The agent runs get_session_history and hands you a clean data set.

Running multiple scripts for setup

Anti-pattern

A developer running one script to create the user, another to get their token, and a third to add them to the group. This is slow and error-prone.

The Fix

Ask your agent to 'Set up new user X in team Y.' The agent executes create_account followed by add_team_member in sequence.

Assuming a token works

Anti-pattern

The system fails with an authentication error because the access token expired overnight, requiring manual intervention and service downtime.

The Fix

Periodically or upon setup, run refresh_user_token. This keeps the connection alive so your agent doesn't fail when it needs to send a message.

When It Fits, When It Doesn't

Use this server if your business process is fundamentally tied to high-volume chat operations: user onboarding, group moderation, or support auditing. If you need to know who spoke to whom and when, this is necessary. Don't use it just because you have a communication problem; use it only if the solution requires modifying state (creating accounts, changing membership) or reading historical message payloads (get_session_history). If all you need is simple data retrieval—like listing user names without knowing their chat history—a dedicated directory service might be easier. But for anything involving real-time communication lifecycle management, this is your tool.

Questions you might have

How do I check chat history using get_session_history? +

You provide the agent with two user IDs and a specific date range. The agent runs get_session_history and returns all messages exchanged between those users within that time window.

What is the difference between send_p2p_message and send_batch_message? +

Use send_p2p_message for a one-to-one private chat. Use send_batch_message when you need to send the exact same message content out to many different users at once.

How do I manage team members using add_team_member? +

You ask your agent to run add_team_member, specifying the target team ID and the user's unique account ID. The agent handles the join action for you.

Does update_account handle all profile changes? +

It updates specific details on an existing IM account, like changing the display name or updating core credentials, keeping your user data current without recreating the whole account.

If my user token expires, how does the `refresh_user_token` tool help me maintain connectivity? +

The refresh_user_token tool automatically retrieves and updates your IM access credentials. It validates your existing connection without requiring you to re-authenticate or manually input new security keys. This keeps your agent connected and ready for real-time chat operations.

What are the necessary parameters required when I use `create_account`? +

You must provide a unique account ID (accid) and establish initial login credentials. The tool will prompt you to confirm if you need to set up any default display names or custom tokens immediately after creation. This ensures the account is fully operational right out of the gate.

When I run into rate limits with `send_batch_message`, what should my agent do? +

If batch messaging fails due to volume, your agent should break the target list into smaller chunks and retry sending messages. The API is designed to handle bulk operations but requires controlled pacing for high-volume sends. Sending in batches of 50 is usually a good starting point.

Does `kick_team_member` automatically notify the user that they have been removed from the team? +

The tool performs the removal action immediately, but it does not send an automated notification message. If you need to inform a kicked member, your agent must follow up with a separate P2P or broadcast message after running kick_team_member.

How do I find my Yunxin AppKey and AppSecret? +

Log in to the Yunxin Console, select your application from the dashboard, and you will find your AppKey and AppSecret in the application details overview.

What is an accid? +

An accid is a unique account identifier for a user in the Yunxin IM system. It is defined by you during account creation and used for all subsequent user-related operations.

How does the CheckSum authentication work? +

Yunxin requires a dynamic CheckSum in the HTTP header for every request. This server automatically calculates it for you using the SHA1(AppSecret + Nonce + CurTime) formula, ensuring secure authorized access.

Connect to your AI in seconds.

Add team member

Create account

Create team

Netease Yunxin / 网易云信: 10 Tools for Comms Ops

Make your AI actually useful.

Add Team Member

Create Account

Create Team

Get Session History

Get Team Detail

Kick Team Member

Refresh User Token

Send Batch Message

Send P2p Message

Update Account

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

Managing group membership shouldn't feel like a database query.

Netease Yunxin / 网易云信 MCP Server: Control the entire user lifecycle.

What your AI can actually do with this

Account Setup and Maintenance

Group Creation and Moderation

Sending Targeted Messages

Reviewing Communication History and Metadata

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

New Employee Onboarding

Crisis Communications

Investigating User Behavior

Team Restructuring

The honest tradeoffs

Trying to check history manually

Running multiple scripts for setup

Assuming a token works

When It Fits, When It Doesn't

Questions you might have