Serve a secret to an agent exactly N times from locked RAM, then wipe it and self-destruct.
Burn-after-reading secrets for AI agents. Your MCP configs are full of plaintext API keys, and every agent you run can read all of them — and they keep working long after the agent is done. dazai inverts that: secrets live in locked, non-swappable RAM, are served to agents over MCP, and are destroyed after N reads — or the instant your session Point any MCP client at it and call once → you…
La vérification confirme l’identité de l’éditeur (la propriété du dépôt), pas la sûreté du code. L’analyse de sécurité couvre les CVE connues et les scripts d’installation suspects.
Forge n’a aucune analyse enregistrée pour cette entrée et n’a donc aucune observation de sa surface d’outils. C’est une absence de preuve, pas la preuve qu’elle n’expose aucun outil.
Burn-after-reading secrets for AI agents. Your MCP configs are full of plaintext API keys, and every agent you run can read all of them — and they keep working long after the agent is done. dazai inverts that: secrets live in locked, non-swappable RAM, are served to agents over MCP, and are destroyed after N reads — or the instant your session Point any MCP client at it and call once → you receive → the server wipes the value out of locked memory and s itself. Call again → the process is gone.…