Traditional artificial intelligence applications have long been trapped in an awkward situation-they have strong understanding and reasoning capabilities, but they have always been isolated from the closed loop of real-world operations. It's like a genius consultant who can only "move his mouth but not his hands": he can analyze data, write reports, and make recommendations, but he can't press any of the execution buttons himself. When users need to translate AI analysis into practical actions, the "last meter" gap still needs to be crossed manually-you still need to manually open another system, enter instructions, and confirm execution. The emergence of MCP server functions is fundamentally changing this landscape. As the "universal connector" for AI, MCP provides a standardized way for AI models to discover, access, and understand real-time data scattered across disparate systems. And when this unified context-aware capability is deeply integrated with Awesun remote control technology, a qualitative leap takes place: Awesun AweSun MCP allows AI to have both "eyes to perceive the world" and "hands to intervene in the world" for the first time ".

1. Awesun what AweSun MCP can do

Professional remote control capability: Directly encapsulates the Awesun mature remote control system, so that AI remote control also has stability, safety and compatibility.

Visual execution of automated O & M: AI automated execution of operations such as troubleshooting and performance optimization. Integrating the capability of "visual recognition and automatic operation of external large models", AI can * * "operate whatever you see" * *-identify interface elements through screenshots, analyze the current state, and then automatically trigger corresponding operations, completing intelligent desktop automation in three steps, greatly improving operation and maintenance efficiency. And compared to the command line operation, the "visual desktop operation" approach allows every step of the AI to be traced. For example, just send the text command "screenshot" to the AI client, and it will automatically capture the screen of the current remote device and save it.

"Conversational" multi-device management: simply tell AI what you need and it automates tasks like device discovery. The AI can quickly locate the target according to the device name or status, without manually turning over the list, and all operations can be easily done through natural language, thus truly realizing * * "manage multiple devices in a word" * *. For example, if you only need to send a text command "remotely restart the server of 192.168.1.100" to the AI client, the AI client will automatically shut down and restart without manual presence.

Cross-platform seamless collaboration: Full support for Windows and macOS to meet the remote control needs of different platforms. Developers can write code on the local Windows and remotely control applications deployed on Linux servers through MCP protocol. Operation and maintenance personnel can use macOS to manage Windows virtual machines and cloud resources at the same time. The MCP protocol serves as a unified bridge to ensure that " one place initiates, everywhere responds ", making cross-platform collaboration as smooth as silk.

2. Pre-conditions

① In the host environment, upgrade the Awesun client to V16.2.3 or later ( Download ) Install AI clients that support MCP (such as OpenCode, Cherry Studio, etc.)

3. Operation steps

Deploying AweSun MCP Server 3.1

Operation path: [Navigation]-> [Awesun MCP]] (1) In the main control environment, open the Awesun software and open "Enable MCP Server 」; (2) Select the appropriate service type according to the usage scenario: ① Stdio (recommended): Local process communication, applicable to AI clients running locally ② HTTP Streamable: HTTP-based remote communication, applicable to scenarios that require cross-network calls. (3) After the selection is completed, copy the generated configuration information for standby according to the AI client that needs to be accessed currently.

3.2 Configure AI Client

Take OpenCode, Claude Code, and Cherry Studio software as examples to demonstrate the configuration process. It is recommended to use OpenCode for better experience.

3.2.1 OpenCode

Demonstrate the configuration process using OpenCode as an example For those who have no programming experience, it is recommended to download the OpenCode desktop version ( download address )

3.2.1.1 Configuration Model Service

Operation path: [Settings]-> [Server]-> [Provider]] (1) Run the OpenCode desktop version and select a model vendor to connect. (2) After setting up the supplier, enable the corresponding model. It is recommended to use a large model with visual understanding such as Kimi K2.5 or Gemini 2.5 Pro.

(3) In order to better understand the current execution dynamics of the AI, it is recommended to turn on the following switches.

3.2.1.2 Configuring the MCP Server

3.2.1.2.1 New Work Area

Create a new folder as the workspace for the opencode, and then initialize the project as follows.

awesun-mcp-example           // 工作区目录
    ├── AGENTS.md            // 系统提示词
    └── opencode.json        // 工作区配置文件

3.2.1.2.2 Load Workspace

Open the workspace directory with the OpenCode (awesun-mcp-example folder must be selected).

3.2.1.2.3 Configure Workspace Prompt Words

Manually edit the awesun-mcp-example/AGENTS.md memory file and preset system prompt words. Reference link:AweSun MCP sample cue

3.2.1.2.4 Configure Workspace MCP Server

Manually edit the awesun-mcp-example/opencode.json configuration file and paste the MCP configuration information copied from the Awesun client into the file. A complete example is as follows:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "serverName": {
      "type": "local",
      "command": [
    "/Applications/AweSun.app/Contents/Helpers/awesun-mcp-server"
      ],
      "enabled": true,
      "environment": {
        "AWESUN_API_URL": "http://127.0.0.1:8980",
        "AWESUN_API_TOKEN": "xxxxxxx"
      }
    }
  }
}

3.2.1.3 Checking Server Connection Status

After the configuration file is written, restart the OpenCode client to make the configuration take effect. Then verify the connection status as follows: (1) Restart the OpenCode client; (2) Enter the command/mcp in the input box to check the connection status of the MCP server.

As shown above, if the display awesun-mcp-server is connected and the processing is on, the configuration is completed.

3.2.1.4 Function Demonstration

When everything is ready, verify the functionality as follows: (1) Enter/new in the input box to open a new session (2) Enter a message: Help me query the configuration information of xxx devices in the device list

3.2.2 Claude Code

3.2.2.1 Installing the CLI Tools

Take Windows 11 as an example, open the terminal, create a new Windows PowerShell window, and execute the command: irm https://claude.ai/install.ps1 | iex

3.2.2.2 Configuring the MCP Server

3.2.2.2.1 New Work Area

Create a new folder on the computer as the workspace for the claude code, and initialize the project as shown below. awesun-mcp-example-claude // workspace directory ny_CLAUDE. md // memory file . mcp.json // MCP configuration file

3.2.2.2.2 Configure Workspace Prompt Words

Manually edit the awesun-mcp-example-claude/CLAUDE.md memory file and preset system prompt words. Reference link: AweSun MCP Example Prompts

3.2.2.2.3 Configure Workspace MCP Server

Manually edit the awesun-mcp-example-claude/.mcp.json configuration file and paste the MCP configuration information copied from the Awesun client into the file. A complete example is as follows:

{  
    "mcpServers": {  
        "awesun-mcp-server": {  
            "command": "C:\Program Files\Oray\AweSun\flutter\awesun-mcp-server.exe",  
            "env": {  
                "AWESUN_API_URL": "http://127.0.0.1:8908",  
                "AWESUN_API_TOKEN": "MTMxNjU1xxxxxxxxxxxxxxxxxxYTktMDkzMmVjN2IyY2Y2"  
            }  
        }  
    }  
}  

3.2.2.3 Configure model services

The preparation work is basically ready. Next, you need to access the large model. Please follow the following steps: Open the resource manager, right-click "This Computer", select "Properties", enter "Advanced System Settings", and then click "Environment Variables". Create a new relevant environment variable according to the following table

Variable name	Value
ANTHROPIC_BASE_URL	https://api.kimi.com/coding/
ANTHROPIC_API_KEY	sk-kimi-xxxxx (your kimi key)

3.2.2.3.1 Load Workspace

(1) Find the workspace directory just created in the explorer and enter (2) Enter the command claude in the explorer address bar, and then enter to load the Claude terminal Note: The first entry needs to be confirmed. Select Yes.

3.2.2.3.2 Check Work Area Status

Enter the command/status enter in the Claude terminal to view the output result. If Anthropic base URL appears: https://api.kimi.com/coding则代表环境变量配置成功 。 If awesun-mcp-server ·✔then the MCP server configuration was successful.

3.2.2.4 Function Demonstration

Verify as follows: (1) If the current stay in the status page, press the ESC key in the Claude terminal to return to the home page until the output box appears. (2) Enter a message: Help me query the configuration information of xxx devices in the device list.

Note: By default, claude code calls each tool to be manually confirmed by the user. If the whole process needs to run automatically, you can use the claude -- dangerously-skip-permissions to re-enter the terminal.

3.2.3 Cherry Studio

Generally not recommended, because the implementation effect is not as good as the first two. However, if you want a simple experience and think the above configuration is too complicated, you can try Cherry Studio.

3.2.3.1 Import MCP Configuration

Operation path: [setting]-> [mcp server]] (1) Open Cherry Studio and enter [Settings] → [MCP Server]]; (2) Click "add" and select "import from JSON 」; (3) Paste the copied Awesun server configuration information into the input box and click OK. (4) After the import is successful, ensure that the MCP server status is Enabled 」.

3.2.3.2 Configuration Model Service

Operation path: [Settings]-> [Model Service]] Enable a model provider as the underlying model for testing MCP functions (such as Alibaba Cloud Model).

3.2.3.3 Test the MCP function

Cherry Studio provides a general-purpose assistant by default for simple testing of MCP functionality.

3.2.3.3.1 Configure Generic Assistant

(1) Return to the Cherry Studio homepage, select the default assistant and edit; (2) Set the MCP server to manual (or automatic), and check the awesun-mcp-server; (3) Model setting Preset model: It is recommended to select a model that supports visual recognition capabilities so that the model can analyze the content of screenshots. If the visual function is not required, a normal text inference model is sufficient. Adjust model parameters: To prevent context loss, it is recommended to set the number of contexts to more than 10

3.2.3.3.2 Setting Prompt Words

To help the large model better understand the purpose of the MCP tool, it is recommended to configure preset prompts: Reference link: AweSun MCP Example Prompts

3.2.3.4 Function Demonstration

After the above configuration is completed, you can enter instructions in the dialogue interface for testing. For example: "look at the configuration information of the game host" or "initiate remote control of the game host". The AI will call the appropriate MCP tool according to your instructions to automate the operation.

4.Q&A

(1) Why did my AI remote control fail?
For device security reasons, the remote control must verify the access password/system account password, AI cannot automatically obtain your password. You only need to manually and successfully remote control the equipment once, and then the AI can help you to remote control normally.

(2) Why did my AI not operate successfully on the remote desktop? Desktop automatic operation requires strong picture recognition ability. It is recommended that you switch to a large model with stronger visual ability such as kimi-2.5, and the success rate will be higher.

5. Appendix: AweSun MCP Tool Documentation

AweSun MCP Server provides Awesun client operation capabilities, including three types of tools: device management, remote control session, and desktop operation. ( View details )

6. Advanced play

(1) The skills of some scenario use cases are used as examples to improve the efficiency and accuracy of AI execution tasks for processes, and can cover some of the functions of traditional RPA. ( View details )

(2) Based on the Awesun MCP service, it provides tool calls for progressive disclosure for AI Agents that support Skills, such as Claude Code, Open Code, and OpenClaw. ( View details )