MCP

302 AI Studio deeply integrates the MCP (Model Context Protocol), enabling AI to connect with external tools and data sources.

What is MCP?

MCP (Model Context Protocol) is an open protocol standard introduced by Anthropic to standardize how AI applications connect with external data sources and tools.

Configure MCP Services

Access MCP Configuration Page

Navigate to Settings and find the MCP option to access the MCP server management page.

Here you can:

• View added MCP services
• Search available MCP services
• Import or add new MCP services

Add MCP Services

Method 1: Import via JSON

Click the Import button in the top right corner and enter your JSON configuration in the dialog.

JSON configuration format:

{
  "mcpServers": {
    "service_name": {
      "command": "command",
      "args": ["argument_list"],
      "env": {
        "ENV_VARIABLE": "value"
      }
    }
  }
}

Method 2: Manual Add

Click the Add button in the top right corner to access the service configuration page.

Fill in the configuration:

• Name: Service name (required)
• Type: Select Streamable HTTP or other types
• Icon: Optional icon selection
• URL: Service URL (required)
• Advanced Settings: Additional configuration options

Usage Guide

Open MCP Server in Login Settings

Navigate to Settings and find the MCP Management option.

Enter Name and Select Tools to Configure

This is the Current Available Tools List, Tools are Continuously Updated

View Server Configuration After Creation

Different Servers use different Keys to retrieve tool configurations. The client only needs to be installed once, no need for repeated installations. Switching between different Servers only requires changing the API KEY.

Use MCP in Conversations

After configuration, you can directly invoke MCP services in the chat interface. Click the MCP icon in the input box to search and select the service you need.

Troubleshooting