TokenToSeaMCP Hub
中文 Console

Audit AI skill safety before you ship. Static + semantic + adversarial audit pipeline for SKILL.md, Codex skill.yaml, Claude Code commands, and OpenCode. Free hosted tier on tarai.dev.

Setup

Choose your client, copy the config, then fill in any required environment variables.

Add to CursorAdd to VS Code

claude mcp add tar-engine --env TAR_ENGINE_BYOK_OPENAI_KEY='<TAR_ENGINE_BYOK_OPENAI_KEY>' --env TAR_ENGINE_BYOK_ANTHROPIC_KEY='<TAR_ENGINE_BYOK_ANTHROPIC_KEY>' -- uvx tar-engine

Environment variables

  • TAR_ENGINE_BYOK_OPENAI_KEY
  • TAR_ENGINE_BYOK_ANTHROPIC_KEY

Replace the placeholders with your own credentials and keep them out of version control.