Writing Assistant Ai MCP Server

This MCP server implements a writing assistant toolkit with authentication and rate limiting via an auth_middleware layer. However, several security and design concerns lower the score: the authentication system relies on client-provided API keys without server-side validation of format, the rate limiting uses local file-based state that can be manipulated, sensitive upgrade URLs are hardcoded throughout the codebase, and the auth middleware imports are path-dependent which reduces robustness. The core writing tools themselves are safe (no dangerous operations, no exfiltration), but the monetization/auth layer introduces moderate risks. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.

7 files analyzed · 14 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.