Skip to content

Encrypted Artifacts

Store sensitive agent outputs — API keys, credentials, private analysis, PII-containing data — in a private vault with end-to-end encryption. The server never sees the plaintext.

  • MCP server configured and connected to your agent
  • TUSKYDP_PASSWORD set in the MCP config (required for private vault encryption)

Tools used: tusky_vault_create, tusky_file_create, tusky_file_read

Private is the default visibility, so no flag is needed:

tusky_vault_create({ name: "sensitive-artifacts" })

The MCP server encrypts it automatically with AES-256-GCM before it leaves the agent’s machine:

tusky_file_create({
name: "api-audit-results.json",
content: "{\"exposed_keys\": [...], \"recommendations\": [...]}",
encoding: "utf-8",
vaultId: "<vault-id>"
})

Use base64 encoding for binary files like certificates or keys:

tusky_file_create({
name: "certificate.pem",
content: "<base64-encoded-content>",
encoding: "base64",
vaultId: "<vault-id>"
})

Decryption is transparent — the MCP server handles it automatically:

tusky_file_read({ fileId: "<file-id>" })
  • Storing security audit results or vulnerability reports
  • Persisting credentials or certificates that agents need across sessions
  • Saving PII-containing analysis (user data, personal information)
  • Any data that must not be readable by the storage provider
  • Client-side encryption — files are encrypted with AES-256-GCM before leaving the agent’s machine
  • Per-file keys — each file gets its own random 256-bit key, wrapped with the master key
  • Server never sees plaintext — the Tusky API only stores encrypted bytes and wrapped keys
  • Passphrase-based access — only someone with the passphrase can derive the master key and decrypt

See the encryption guide for the full cryptographic details and key hierarchy.