MCPSafe.io
RegistryThreatsMethodologyDocsPricingScanSign in
MCPSafe.io

Security checks for MCP servers — public packages and private repos, fast or deep.

Legal

Privacy PolicyCookie PolicyTerms of ServiceSecurity disclosure

Resources

State of MCP SecuritySupportSystem statusMade in Germany 🇩🇪

© 2026 MCPSafe. All rights reserved.

GDPR — Privacy Policy
← Registry
—

@gramatr/mcp

Not yet scanned · npm

$npm install @gramatr/mcp
Downloads: 28,826

Ready to scan

This package is in MCPSafe’s catalog but hasn’t been scanned yet. Run a Fast scan for rules + CVE findings in under 5 minutes, or a Deep scan to add LLM consensus review across 5 judges (sign in required, up to 20 min).

About

grāmatr — Intelligence middleware for AI agents. Pre-classifies every request, injects relevant memory and behavioral context, enforces data quality, and maintains session continuity across Claude, ChatGPT, Codex, Cursor, Gemini, and any MCP-compatible cl

What a scan checks

  • Threats40+ rules: prompt injection, destructive tool schemas, IAM wildcards, OAuth over-scope, install-time hooks, and more.
  • Known CVEsMatches package + dependency versions against NVD and GHSA advisory databases.
  • Supply chainTyposquat detection, malware indicators, suspicious install hooks, and maintainer signals.
  • Runtime safetySecret exfiltration paths, overbroad schemas, destructive operations without confirmation, and schema robustness.