Runtime verification and receipt verification for AI agents — tool-call guardrail, CCS 7-dimension standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking, Ed25519 signed
{ "mcpServers": { "correctover": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}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 correctover -- npx -y correctover@2.4.18在終端機中執行。
{ "mcpServers": { "correctover": { "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
總覽
Runtime verification and receipt verification for AI agents — tool-call guardrail, CCS 7-dimension standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking, Ed25519 signed tamper-evident receipts. Framework-agnostic.
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。
Correctover 透過 stdio 在本機執行。
上次檢查時間:2026-11-05。 Runtime verification and receipt verification for AI agents — tool-call guardrail, CCS 7-dimension standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking, Ed25519 signed tamper-evident receipts. Framework-agnostic.
來自發布者
尚未爬取 README。 開啟儲存庫
Runtime verification and receipt verification for AI agents — tool-call guardrail, CCS 7-dimension standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking, Ed25519 signed tamper-evident receipts. Framework-agnostic.