Yunxin MCP Server

What does “yunxin” MCP Server do?

The yunxin MCP (Model Context Protocol) Server is designed to bridge AI assistants with NetEase Yunxin’s IM (Instant Messaging) and RTC (Real-Time Communication) services. By exposing a set of tools that facilitate access to messaging and real-time communication data, yunxin-mcp-server enables AI-powered workflows for tasks such as querying chat histories, managing group communications, monitoring RTC quality metrics, and aggregating application statistics. This integration empowers developers and operators to automate operations, analyze messaging trends, monitor RTC health, and improve user experiences by making relevant data and actions accessible to LLM-based agents and external systems.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

No explicit resources are listed in the repository or documentation.

List of Tools

• send_p2p_msg / send_team_msg
  Send individual or group chat messages, given sender/receiver accounts or group IDs. Useful for automating operational or notification messages.
• query_p2p_msg_history / query_team_msg_history
  Query individual or group chat histories within a time range, supporting operations and analytical workflows.
• query_application_im_daily_stats
  Retrieve daily IM application statistics such as daily active users, message volumes, storage, and callback metrics.
• query_rtc_room_members / query_rtc_room_members_by_uids
  Fetch RTC room member details, including online duration, location, ISP, and device information.
• query_rtc_room_stuck_rate / query_rtc_room_user_stuck_rate
  Access audio/video stutter rate metrics at room or user granularity for monitoring service quality.
• query_rtc_room_top_20
  List top 20 RTC rooms by metrics like active users, join latency, audio/video stutter rates, and network delays.

Use Cases of this MCP Server

• Automated Messaging Operations
  Automate the sending of IM operational messages to individuals or groups, improving outreach and engagement.
• Historical Data Analysis
  Retrieve and analyze chat histories for compliance, customer support, or operational insight.
• Application Health Monitoring
  Monitor daily application statistics to detect anomalies, track user activity, and ensure service reliability.
• RTC Quality Monitoring
  Track room and user-level RTC metrics to identify and address quality issues proactively.
• Room Analytics and Reporting
  Aggregate and analyze top-performing RTC rooms to optimize infrastructure and enhance user experience.

How to set it up

Windsurf

1. Ensure Python and required dependencies are installed.
2. Locate the Windsurf configuration file (e.g., .windsurf/config.json).
3. Add yunxin MCP server in the mcpServers section with the appropriate command and arguments.
4. Save the file and restart Windsurf.
5. Verify that the yunxin MCP server appears in the interface.

{
  "mcpServers": {
    "yunxin-mcp": {
      "command": "yunxin-mcp-server",
      "args": []
    }
  }
}

Claude

1. Install Python and dependencies for yunxin-mcp-server.
2. Find Claude’s MCP server configuration file.
3. Insert the following JSON snippet into the MCP configuration.
4. Save and restart Claude.
5. Confirm yunxin-mcp-server functionality.

{
  "mcpServers": {
    "yunxin-mcp": {
      "command": "yunxin-mcp-server",
      "args": []
    }
  }
}

Cursor

1. Ensure Python and dependencies are installed.
2. Open Cursor’s settings or configuration file.
3. Add yunxin MCP server to the mcpServers section.
4. Save changes and restart Cursor.
5. Check for yunxin MCP integration.

{
  "mcpServers": {
    "yunxin-mcp": {
      "command": "yunxin-mcp-server",
      "args": []
    }
  }
}

Cline

1. Install Python and yunxin-mcp-server dependencies.
2. Access Cline’s configuration file.
3. Register yunxin MCP server with the following JSON.
4. Save and restart Cline.
5. Validate the server is active.

{
  "mcpServers": {
    "yunxin-mcp": {
      "command": "yunxin-mcp-server",
      "args": []
    }
  }
}

Securing API Keys:
Use environment variables to protect sensitive credentials. Example with env and inputs:

{
  "mcpServers": {
    "yunxin-mcp": {
      "command": "yunxin-mcp-server",
      "args": [],
      "env": {
        "YUNXIN_API_KEY": "${YUNXIN_API_KEY}"
      },
      "inputs": {
        "api_key": "${YUNXIN_API_KEY}"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "yunxin-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “yunxin-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

I would rate this MCP server a 6/10. It provides clear tool APIs and setup instructions, but lacks prompt templates, resource definitions, and explicit support for advanced MCP features (roots, sampling).

MCP Score