MCP Safeguard
未认领🛡️ Automated security scanner for MCP (Model Context Protocol) servers — 52 rules for prompt injection, credential exposure, SSRF & tool poisoning. pip install mcp-safeguard
ai-securityclaudellm-securitymcpmodel-context-protocolprompt-injectionpythonsecurity-scannercursoragentic-ai
安装
$
python -m fastmcp run src/mcp_safeguard/server.py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
7 个工具中显示 7 个
文档中列出的工具 (7)
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。
check_auth_config
Audit server config for credential exposure and OAuth scope risks
check_endpoint_exposure
Probe for exposed admin/debug endpoints and dangerous ports
compare_scans
Diff two scans to detect regressions
generate_security_report
Get report in HTML, JSON, or text
get_scan_history
List all past scans with severity scores
scan_mcp_server
Full scan of an MCP server: injection + credentials + endpoints + tools
scan_tool_definitions
Analyze tool JSON for injection and poisoning