DocsICP FilingConsole
官方文档
首页

Integrate OpenClaw with QQ

更新时间：
复制 MD 格式
产品详情
我的收藏

This document describes how to integrate the OpenClaw service with QQ, allowing you to use natural language to interact with OpenClaw in a direct chat with a QQ bot.

Before you begin

Before you configure a channel, you must purchase and configure a Simple Application Server instance with the OpenClaw application image by following the steps below or the instructions in Deploy an OpenClaw image. If you have already done this, you can skip this section.

Purchase and configure a Simple Application Server instance with the OpenClaw application image

Step 1: Purchase an OpenClaw package

Important

If you have already purchased a Simple Application Server, you can skip this step and deploy OpenClaw by resetting the system. When you reset the system, select the OpenClaw image under Application Images. However, resetting the system erases all data on the system disk of the Simple Application Server. Make sure that you back up your data as needed. For more information, see Reset system.

  1. Purchase a Simple Application Server instance pre-installed with the OpenClaw application.

  2. The Simple Application Server page has preset resource configurations. If you need to change them, review the following details:

    • Servers: Memory must be 2 GiB or higher. You can switch packages based on your requirements.

    • Region: The default region is China (Beijing).

    • Purchase Settings: The default subscription period is 12 months. You can change the duration as needed.

Step 2: Configure OpenClaw

OpenClaw provides two configuration methods. Select the tab for your image version below to view the instructions.

OpenClaw 2026.5.19 and later (recommended)

  1. Log on to the Simple Application Server console, click the instance ID on the server card, and then click the Server Overview tab on the Application Details page.

  2. On the Application Details page, click the Initialize button in the lower-left corner and follow the wizard to complete Step 1: Model Configuration.

    • Large Model Platform: Select a model provider from the drop-down list. Supported providers include Alibaba Cloud Model Studio Token Plan (Team Edition), Alibaba Cloud Model Studio Coding Plan, Alibaba Cloud Model Studio, DeepSeek, Kimi, GLM Coding Plan, and Zhipu.

    • API key: Select the region for your API key and enter the API key.

    • Model: Select or manually enter the model name.

    After completing the configuration, click Configure Now to proceed to the next step.

  3. In Step 2: Use Web UI of the initialization wizard, first click Allow Access in the Allow OpenClaw Access Port area to open the port. Then, click Log in to Web UI to access the OpenClaw Web UI and start a conversation with the OpenClaw agent.

    Important

    Opening the port exposes the service to the public internet. After initialization, you can disable public access with the Public access switch in the status bar at the top of the Application Details page. For more information, see How to enable or disable public access to the OpenClaw Web UI.

  4. (Optional) View the token. After initialization, you can copy the full token by clicking the copy button next to the token field in the status bar at the top of the Application Details page.

    Warning

    Do not disclose the full URL that contains the token. This link includes authentication credentials, and anyone with this link can bypass login verification and gain administrator access to the OpenClaw console.

OpenClaw before 2026.5.19

  1. In the Simple Application Server console, click the instance ID on the server card, and then click the Server Overview tab on the Application Details page.

  2. In the OpenClaw Usage Steps area, under Allow Port Access, click Run Command to open the firewall for the OpenClaw service runtime port.

    Important

  3. Click Run Command under Run Command to configure the Model Studio API key.

    You can configure two types of Model Studio API keys:

    • Coding Plan exclusive API key (recommended): This is a fixed monthly fee model that provides a monthly request quota. Calls that exceed the quota will fail without incurring charges, which helps prevent unexpected costs.

      The Coding Plan currently supports models such as qwen3.5-plus, kimi-k2.5, MiniMax-M2.5, and glm-5. For a detailed list of models, see Coding Plan overview.

    • Pay-as-you-go Model Studio API key based on token usage.

    Configure the API key. Select the Coding Plan API key from the drop-down list or directly enter the pay-as-you-go API key. After selecting a model, click Next.

    If you manually enter an API key, ensure that the selected region matches the region of the API key. Otherwise, calls to the model may fail.
    Important

    The Model Studio Token Plan is not supported during the initial configuration process. Attempting to enter it will cause an error. If you need to use the Token Plan, complete the initialization first, and then refer to How do I connect to the Model Studio Token Plan Team Edition in OpenClaw? for configuration.

  4. Under Access Web UI panel, click Run Command to obtain the URL for the OpenClaw Web UI. You can then interact with the OpenClaw agent.

    You can disable public access to the Web UI at any time if needed. For more information, see Disable public access to the OpenClaw Web UI.

  5. (Optional) View the token.

    Navigate to Application Details > Basic Configuration > View token and click View to retrieve and save the token.

    Warning

    Do not disclose the full URL that contains the token. This link includes authentication credentials, and anyone with this link can bypass login verification and gain administrator access to the OpenClaw console.

Integrate with QQ

OpenClaw provides two ways to integrate with QQ. Select the tab that matches your image version.

OpenClaw 2026.5.19 and later (recommended)

The recommended QR code method does not require you to register as a developer. The integration activates automatically after authorization.

  1. Log on to the Simple Application Server console, find your target OpenClaw server, and go to the Application Details tab.

  2. In the Channels card, click Add Channel.

  3. From the channel drop-down list, select QQ.

  4. On the default Connect via QR Code tab, click Configure with QR Code.

  5. Use the QQ mobile app to scan the QR code in the pop-up window. Follow the prompts to complete the authorization. The integration then activates automatically.

Versions earlier than OpenClaw 2026.5.19

You must manually create a bot on the QQ Open Platform and enter the AppID and AppSecret into the console.

1. Create a QQ bot

  1. Go to the official Tencent QQ Open Platform website. In the product section, click Use Now.

  2. In the mobile sign-in area, scan the QR code to sign in to your QQ account.

  3. Click Create Bot to generate a new QQ bot. Save the bot's AppID and AppSecret.

    Important

    Store your key information securely. The AppSecret (bot secret) for a QQ bot cannot be stored or viewed in plaintext. If this is your first time viewing it, or if you forget it, you must regenerate it.

2. Integrate OpenClaw with QQ

The OpenClaw plugin integration method is only supported for instances with image version OpenClaw 2026.2.9 or later. To integrate this channel on an older version, see Integrate a channel by using AppFlow. You can view the current image version of your instance in the Basic Information > Image information section of the Simple Application Server overview page.

Configure the channel in the console. In Application Details > Channel Configuration, enter the AppID and AppSecret that you obtained when you created the bot, and then click Apply.

Verify the integration

In QQ, start a chat with the bot you created.

Previous：Integrate OpenClaw with WeComNext：OpenClaw web page integration