72hours security check for Claude.ai

io.github.maebsy/72hours

Scan a public GitHub repo, explain risks, get fix prompts and rescan to confirm fixes.

client:Claude.ai transport:streamable-http tools:15

Install 72hours security check in Claude.ai

Settings → Connectors → Add custom connector

https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc

Claude on the web takes a remote URL and completes OAuth in the browser. For a packaged server use Claude Desktop or Claude Code instead. Claude.ai docs

What Claude.ai can do once it is connected

service_info
create_workspace
close_workspace
start_scan
get_scan
start_analysis
get_analysis
get_fix_prompt
rescan
generate_report
incident_report
audit_repository
audit_status
check_fix
verify_demo

72hours security check in other clients

Claude Code
Claude Desktop
Cursor
VS Code
Zed
Windsurf
Cline
Gemini CLI
Grok
ChatGPT
LangChain

72hours security check MCP server