接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y [email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add io.github.aakashbhardwaj27-ai-scanner -- npx -y ai-scanner-mcp@1.0.3在終端機中執行。
{ "mcpServers": { "io.github.aakashbhardwaj27-ai-scanner": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.
check_secrets | Security check — pass/fail scan for exposed credentials only. Perfect for pre-commit checks |
ai_inventory | AI stack overview — which SDKs, frameworks, models, and API endpoints are used (no secret detection) |
claude mcp add ai-scanner npx ai-scanner-mcp
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ai-scanner": {
"command": "npx",
"args": ["ai-scanner-mcp"]
}
}
}
Config file location:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonAdd to .cursor/mcp.json in your project:
{
"mcpServers": {
"ai-scanner": {
"command": "npx",
"args": ["ai-scanner-mcp"]
}
}
}
Add to ~/.windsurf/mcp.json:
{
"mcpServers": {
"ai-scanner": {
"command": "npx",
"args": ["ai-scanner-mcp"]
}
}
}
Once connected, you can ask your AI agent:
Full scan with all detection categories. Parameters:
Security-focused pass/fail check. Parameters:
AI stack awareness (no secret detection). Parameters:
Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.
{ "mcpServers": { "io.github.aakashbhardwaj27-ai-scanner": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
AI Scanner 透過 stdio 在本機執行。
上次檢查時間:2026-11-08。 Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.