[Model Context Protocol (MCP)](https://antigravity.google/docs/mcp) is an open standard that enables
developers to build secure, two-way connections between AI assistants and data
sources or tools.

Integrating Unity's MCP server with Google's Antigravity allows an AI agent in
the IDE to interact directly with the Unity Editor. This enables the agent to
seamlessly execute editor operations---such as capturing the active scene view---to
streamline your game development workflow.

## Setup Unity MCP for Antigravity IDE

1. Install [Antigravity IDE](https://antigravity.google/download).
2. Install Unity's AI Assistant package following [Unity's official
   documentation](https://docs.unity3d.com/Packages/com.unity.ai.assistant@2.14/manual/install/install-chat.html).
3. Open the **Project Settings** window and go to **AI \> Unity MCP Server**.
4. Go to **Integrations \> Gemini** , click **Configure** , and confirm that the
   indicator turns green and the status changes to **Configured**.

   ![Unity MCP settings showing the Gemini integration as Configured with a green status indicator.](https://developer.android.com/static/games/engines/unity/images/unity-mcp-integrations-settings.png) **Figure 1.** Gemini integration configured successfully in the Unity MCP settings.
5. Ensure that the **Unity Bridge** status is **Running**.

   ![Unity MCP settings showing the Unity Bridge status as Running.](https://developer.android.com/static/games/engines/unity/images/unity-bridge-setting.png) **Figure 2.** Ensuring the Unity Bridge status is Running.
6. Go to **Tools** and select the tools that you need for your workflow.

   ![Unity MCP settings with various tools selected under the Tools section.](https://developer.android.com/static/games/engines/unity/images/unity-mcp-tools-setting.png) **Figure 3.** Selecting the tools to enable for the Unity MCP server.
7. Go to **Integrations** and click the copy button under
   **Example Configuration** to copy the configuration text.

   ![Unity MCP settings showing the Example Configuration text field and a copy button.](https://developer.android.com/static/games/engines/unity/images/unity-mcp-example-config.png) **Figure 4.** Copying the Example Configuration from Unity's MCP settings.
8. Go to **Integrations \> Gemini \> Locate** to open the destination folder, then
   paste the configuration copied in the previous step into `settings.json` and
   save the file.

9. Open the Antigravity IDE, go to the **Agent** window, click the three-dot
   menu, select **MCP Servers \> Manage MCP Servers** , open the **Manage MCPs** tab,
   click **Refresh** , and confirm that **unity-mcp** is configured.

   ![Antigravity IDE Manage MCPs window displaying unity-mcp as configured.](https://developer.android.com/static/games/engines/unity/images/antigravity-ide-manage-mcp-window.png) **Figure 5.** Verifying unity-mcp is configured in the Antigravity IDE Manage MCPs window.

## Example Usage

The following is an example of using Gemini within the Antigravity IDE to play a
Unity scene and seek feedback on its visuals.

1. In the Antigravity IDE, open the **Agent** window and enter a prompt to request feedback on your scene's visuals.

   ![Antigravity IDE Agent window displaying a prompt that requests a visual audit of the active Unity scene.](https://developer.android.com/static/games/engines/unity/images/antigravity-example-prompt.png) **Figure 6.** Querying the AI agent to request feedback on the active Unity scene.
2. The AI agent executes the tools to capture the scene, analyze the graphics, and output the report.

   ![Antigravity IDE showing the resulting visual audit report generated by the agent.](https://developer.android.com/static/games/engines/unity/images/antigravity-resulting-audit-report.png) **Figure 7.** Visual audit report generated by the agent based on the scene's visuals.