MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
@kryptosai/mcp-seatbelt · npm 0.7.0 · stdio
claude mcp add --transport stdio 'mcp-seatbelt' -- npx -y '@kryptosai/mcp-seatbelt@0.7.0'Run in a terminal; adds the server to Claude Code.
@kryptosai/mcp-seatbeltMCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF.
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
Auth0 MCP Server: Manage Auth0 applications, APIs, actions, logs, and forms using natural language
AI agent tools for Open Security Controls Assessment Language (OSCAL)
Find relevant security data from Sentinel data lake for building effective agents. More:aka.ms/s/de
Search and audit NIST NVD CVEs by keyword, severity, CWE, CISA KEV status, and CPE.
Answers EU Digital Product Passport questions: scope, required fields, registry and law changes.
AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.
