stun-mcp
About
STUN(RFC8489)のBinding Requestを送って結果を返すMCPサーバー
Details
- Author
- kadoshita
- Downloads
- 156
- Categories
- Other
Jump to
- Sends STUN Binding Requests (RFC8489)
- Returns the STUN response (mapped address, etc.)
- Works as an MCP server over stdio
- Minimal STUN packet processing (basic implementation only)
- Designed for use with AI agents in VS Code
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
stun-mcpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install Node.js and build the server. Add the following configuration to your mcp.json file (e.g., in VS Code with Agent mode enabled): { "servers": { "stun": { "type": "stdio", "command": "node", "args": ["/path/to/stun-mcp/build/main.js"] } } }. Then prompt your agent to send a STUN request, for example: "以下のURLにSTUNのリクエストを送り、結果を出力してください stun:stun1.l.google.com:19302".
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"stun-mcp": {
"stun": {
"command": "node",
"args": [
"/path/to/stun-mcp/build/main.js"
]
}
}
}
}McpServers
{
"stun": {
"command": "node",
"args": [
"/path/to/stun-mcp/build/main.js"
]
}
}stun-mcp
STUN(RFC8489)のBinding Requestを送って結果を返すMCPサーバー> [!WARNING]
> STUNのパケットの処理は必要最低限のものしか実装していません
利用方法
- Agentモードを有効化したVS Codeでの設定方法です
- mcp.jsonに以下の設定を追加します
{
"servers": {
"stun": {
"type": "stdio",
"command": "node",
"args": [
"/path/to/stun-mcp/build/main.js"
]
},
}
}
- 以下のようなプロンプトを実行すると、STUNのリクエストが送られ、結果が表示されます
> 以下のURLにSTUNのリクエストを送り、結果を出力してください
>
> stun:stun1.l.google.com:19302
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
