Audit and firewall for AI agent MCP server permissions
Stage
Not given
Startup
Founded
Not given
2025
Based in
IN
IN
Pricing model
Freemium
Free
Pricing
Free: 1 scan per month. Top-up: $10 USD (₹799) for 6 scans, one-time purchase. Founder: $22 USD (₹1,799) per month or $220 USD (₹17,990) per year for 36 scans per month. Services from $150 USD (₹12,000).
Not given
Key features
Security score out of 100 with findings ranked by severity
Plain-English vulnerability explanations
Attack path mapping to MITRE ATT&CK techniques
Code map showing which files to fix first
Audit logs of scans, sign-ins and changes
README badge showing current security grade
MCP server for scanning from AI agents
Leaked credential testing and live-key check
MCP server inventory and permissions analysis
Over-permissioned tool detection
Local config analysis in browser
Read-only mode enforcement for databases and APIs
Secret and API key leak blocking
Tool definition pinning to detect rug pulls
Prompt injection detection and flagging
Activity logging and webhook alerts
Team policy management via git repository
What makes it different
Only security scanner built specifically for AI-generated code from tools like Bolt, Cursor and v0
AI-powered false-positive reduction prevents noise in security reports
Automated fix prompts written for the specific AI tool that built the app
Code is deleted after scan completes with no backups or model training
Runs entirely in your browser - no config or token data sent to servers
Free and open source (MIT) with no dependencies
Detects the lethal trifecta of agent security risks