diff --git a/README.md b/README.md
index 917fcb9..6d7b405 100644
--- a/README.md
+++ b/README.md
@@ -100,7 +100,7 @@ Here are some example prompts and their generated diagrams:
 
 ## MCP Server (Preview)
 
-> **Preview Feature**: This feature is experimental and may not stable.
+> **Preview Feature**: This feature is experimental and may not be stable.
 
 Use Next AI Draw.io with AI agents like Claude Desktop, Cursor, and VS Code via MCP (Model Context Protocol).
 
@@ -211,6 +211,8 @@ See the [Next.js deployment documentation](https://nextjs.org/docs/app/building-
 -   OpenRouter
 -   DeepSeek
 -   SiliconFlow
+-   SGLang
+-   Vercel AI Gateway
 
 
 All providers except AWS Bedrock and OpenRouter support custom endpoints.
@@ -219,7 +221,7 @@ All providers except AWS Bedrock and OpenRouter support custom endpoints.
 
 **Model Requirements**: This task requires strong model capabilities for generating long-form text with strict formatting constraints (draw.io XML). Recommended models include Claude Sonnet 4.5, GPT-5.1, Gemini 3 Pro, and DeepSeek V3.2/R1.
 
-Note that `claude` series has trained on draw.io diagrams with cloud architecture logos like AWS, Azure, GCP. So if you want to create cloud architecture diagrams, this is the best choice.
+Note that the `claude` series has been trained on draw.io diagrams with cloud architecture logos like AWS, Azure, GCP. So if you want to create cloud architecture diagrams, this is the best choice.
 
 
 ## How It Works
diff --git a/docs/cn/README_CN.md b/docs/cn/README_CN.md
index 91f7a72..f5a4e4c 100644
--- a/docs/cn/README_CN.md
+++ b/docs/cn/README_CN.md
@@ -93,7 +93,7 @@ https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
 
 ## MCP服务器（预览）
 
-> **预览功能**：此功能为实验性功能，可能会有变化。
+> **预览功能**：此功能为实验性功能，可能不稳定。
 
 通过MCP（模型上下文协议）在Claude Desktop、Cursor和VS Code等AI代理中使用Next AI Draw.io。
 
@@ -241,6 +241,8 @@ npm run dev
 -   OpenRouter
 -   DeepSeek
 -   SiliconFlow
+-   SGLang
+-   Vercel AI Gateway
 
 除AWS Bedrock和OpenRouter外，所有提供商都支持自定义端点。
 
diff --git a/docs/cn/ai-providers.md b/docs/cn/ai-providers.md
index 6a9eec2..25e5e31 100644
--- a/docs/cn/ai-providers.md
+++ b/docs/cn/ai-providers.md
@@ -85,6 +85,19 @@ AI_MODEL=deepseek-ai/DeepSeek-V3  # 示例；使用任何 SiliconFlow 模型 ID
 SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1  # 或 https://api.siliconflow.cn/v1
 ```
 
+### SGLang
+
+```bash
+SGLANG_API_KEY=your_api_key
+AI_MODEL=your_model_id
+```
+
+可选的自定义端点：
+
+```bash
+SGLANG_BASE_URL=https://your-custom-endpoint/v1
+```
+
 ### Azure OpenAI
 
 ```bash
@@ -188,7 +201,7 @@ AI_MODEL=openai/gpt-4o
 如果您配置了**多个** API 密钥，则必须显式设置 `AI_PROVIDER`：
 
 ```bash
-AI_PROVIDER=google  # 或：openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway
+AI_PROVIDER=google  # 或：openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang
 ```
 
 ## 模型能力要求
diff --git a/docs/en/ai-providers.md b/docs/en/ai-providers.md
index d66f118..0f0b0d1 100644
--- a/docs/en/ai-providers.md
+++ b/docs/en/ai-providers.md
@@ -85,7 +85,18 @@ Optional custom endpoint (defaults to the recommended domain):
 SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1  # or https://api.siliconflow.cn/v1
 ```
 
+### SGLang
 
+```bash
+SGLANG_API_KEY=your_api_key
+AI_MODEL=your_model_id
+```
+
+Optional custom endpoint:
+
+```bash
+SGLANG_BASE_URL=https://your-custom-endpoint/v1
+```
 
 ### Azure OpenAI
 
@@ -190,7 +201,7 @@ If you only configure **one** provider's API key, the system will automatically
 If you configure **multiple** API keys, you must explicitly set `AI_PROVIDER`:
 
 ```bash
-AI_PROVIDER=google  # or: openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway
+AI_PROVIDER=google  # or: openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang
 ```
 
 ## Model Capability Requirements
diff --git a/docs/ja/README_JA.md b/docs/ja/README_JA.md
index edbd1bd..b6ce098 100644
--- a/docs/ja/README_JA.md
+++ b/docs/ja/README_JA.md
@@ -93,7 +93,7 @@ https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979
 
 ## MCPサーバー（プレビュー）
 
-> **プレビュー機能**：この機能は実験的であり、変更される可能性があります。
+> **プレビュー機能**：この機能は実験的であり、安定しない可能性があります。
 
 MCP（Model Context Protocol）を介して、Claude Desktop、Cursor、VS CodeなどのAIエージェントでNext AI Draw.ioを使用できます。
 
@@ -242,6 +242,8 @@ Next.jsアプリをデプロイする最も簡単な方法は、Next.jsの作成
 -   OpenRouter
 -   DeepSeek
 -   SiliconFlow
+-   SGLang
+-   Vercel AI Gateway
 
 AWS BedrockとOpenRouter以外のすべてのプロバイダーはカスタムエンドポイントをサポートしています。
 
diff --git a/docs/ja/ai-providers.md b/docs/ja/ai-providers.md
index 945f69f..63d23d6 100644
--- a/docs/ja/ai-providers.md
+++ b/docs/ja/ai-providers.md
@@ -85,6 +85,19 @@ AI_MODEL=deepseek-ai/DeepSeek-V3  # 例; 任意の SiliconFlow モデル ID を
 SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1  # または https://api.siliconflow.cn/v1
 ```
 
+### SGLang
+
+```bash
+SGLANG_API_KEY=your_api_key
+AI_MODEL=your_model_id
+```
+
+任意のカスタムエンドポイント:
+
+```bash
+SGLANG_BASE_URL=https://your-custom-endpoint/v1
+```
+
 ### Azure OpenAI
 
 ```bash
@@ -188,7 +201,7 @@ AI_MODEL=openai/gpt-4o
 **複数**の API キーを設定する場合は、`AI_PROVIDER` を明示的に設定する必要があります:
 
 ```bash
-AI_PROVIDER=google  # または: openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway
+AI_PROVIDER=google  # または: openai, anthropic, deepseek, siliconflow, doubao, azure, bedrock, openrouter, ollama, gateway, sglang
 ```
 
 ## モデル性能要件