SecureCode MCP
未认领Standalone SecureCode MCP server - scan, map, fix, and attack tools for AI coding assistants. @securecode-ai/mcp on npm.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'securecode-mcp' -- 'npx' '-y' '@securecode-ai/mcp@latest' 'serve' '--workspace' '/path/to/your/project'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Security服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
17 个工具中显示 17 个
文档中列出的工具 (17)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
securecode.add-known-fact
Add a project fact for faster investigations
securecode.agent-scan
Agent-mode deep scan with 20+ tools, structured proof, and sandbox verification
securecode.agent-scan-batch
Sequential batch scan: map + architecture scout + scan top N files one at a time
securecode.attack
Endpoint red-team testing (beta)
securecode.clear-agent-memory
Clear all agent memory (or one FP by ID)
securecode.clear-finding-reviews
Clear all finding reviews for a workspace
securecode.decide-finding
Accept or reject a finding in the review queue
securecode.fix
Generate a patch for a specific finding
securecode.get-agent-memory
View learned false positives and known facts
securecode.map
Build project map: endpoints, middleware, auth, architecture context
securecode.record-false-positive
Dismiss a finding as FP — agent learns not to report it
securecode.review-findings
Review the finding queue for a workspace
securecode.run-tests
Run tests in sandbox for verification
securecode.scan
Scan code for vulnerabilities (AI pipeline)
securecode.scan-batch
Scan multiple files in one call
securecode.scan-dependencies
Scan lockfiles for known vulnerabilities (OSV/NVD)
securecode.scan-secrets
Scan for hardcoded secrets and PII (local, no AI)