On this page

Use AI Coding

2026-09-08

With AI Coding (AI-powered coding tools), you can efficiently integrate ZEGOCLOUD products and fix related issues. We provide out-of-the-box Skills for various AI coding tools. Once installed, AI automatically acquires ZEGOCLOUD product domain knowledge and standard workflows, and calls the ZEGOCLOUD Document MCP service to consult official documentation, enabling it to complete tasks such as integrating ZEGOCLOUD products or fixing ZEGOCLOUD-related bugs more accurately.

Skill Capabilities

A capability extension package that is intelligently triggered by AI programming tools and loaded on demand. It automatically injects ZEGOCLOUD product domain knowledge and standard workflows into AI in appropriate scenarios.

CapabilityDescription
Product integrationGuides ZEGO product selection, platform selection, and implementation
Server-side Token generationProvides server-side Token generation sample code in multiple languages
Server-side API callsIncludes signature mechanism descriptions and multilingual call examples
Resource downloadDownloads SDKs, sample projects, sample code, and other resources
Knowledge Q&A and troubleshootingOfficial-documentation-based knowledge Q&A, supporting online issue troubleshooting such as error codes and API usage
Note
The above lists the currently supported capabilities. More will be added continuously.

Step 1: Install Skills

The ZEGOCLOUD Document MCP service achieves better results when used together with Skills: they guide AI to prioritize calling the ZEGOCLOUD Document MCP tools to consult official documentation when integrating ZEGOCLOUD products or troubleshooting issues, and then proceed with development work.

If your AI programming tool does not have a corresponding plugin, please manually download all Skills from the skills directory to the configuration folder of your tool.

Step 2: Configure the ZEGOCLOUD Document MCP Server

The ZEGOCLOUD Document MCP server uses the HTTP protocol. The configuration is as follows:

// !mark(3:5)
{
  "mcpServers": {
    "ZEGOCLOUD": {
      "url": "https://doc-ai.zego.im/mcp/"
    }
  }
}

Please refer to the corresponding documentation for MCP server configuration methods for various IDEs:

Note
Only some popular IDE MCP server configuration methods are listed here. For other IDEs, please refer to their respective documentation.

Other Integration Methods

Claude Code Plugin

If you are using Claude Code, it is recommended to install ZEGO Claude Code Plugins directly. The plugin automatically installs ZEGO-related Skills and configures the ZEGOCLOUD Document MCP service.

DeepSeek Harness Plugin

If you are using DeepSeek Harness, install our dsh-zego-assistant plugin (published on GitHub and npm). The plugin automatically configures the ZEGOCLOUD Document MCP service and installs ZEGO-related Skills. After installation, restart the corresponding profile, and you can see that both zego-assistant and mcp-client are "Enabled" in "Settings > Plugins > Plugin list", which indicates a successful installation:

dsh plugin --profile web add dsh-zego-assistant
DeepSeek Harness plugin list

DeepSeek Harness plugin configuration

Best Practices

  • Your prompts to AI should clearly specify the ZEGOCLOUD product names and platforms being used.
  • Your prompts to AI should include as many detail requirements as possible so that AI can better understand user needs.
  • If errors occur after integration, clearly describe the error phenomenon and include error logs or error message screenshots so AI can better locate the problem.

Demo

The following is a demo video of using Augment Code connected to the ZEGO MCP server to have AI integrate the ZEGO Real-time Interaction AI Agent product into an existing project:

Previous

How to upgrade UIKits with a plugin to V2.0.0?

Next

Why is haptic feedback ineffective on iOS devices during stream publishing?

On this page

Back to top