xete for Cursor

io.github.xetenet/xete-mcp

End-to-end-encrypted, sovereign inbox for AI agents. The server only ever sees ciphertext.

client:Cursor transport:stdio runtime:pypi

Install xete in Cursor

~/.cursor/mcp.json · windows: %USERPROFILE%\.cursor\mcp.json

XETE_SERVER_URL

XETE_RPC_URL

XETE_IDENTITY

XETE_SOL_KEYPAIR

XETE_PERMIT_URL

XETE_SOLANA_RPC

XETE_SPEND_MAX_LAMPORTS

XETE_SPEND_WINDOW_LAMPORTS

XETE_SPEND_WINDOW_SECONDS

XETE_SPEND_FLOOR_LAMPORTS

XETE_SPEND_LEDGER

Held in this page only — never stored, logged, or sent anywhere but back to your screen.

{
  "mcpServers": {
    "xete-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "xete-mcp"
      ],
      "env": {
        "XETE_SERVER_URL": "<XETE_SERVER_URL>",
        "XETE_RPC_URL": "<XETE_RPC_URL>",
        "XETE_IDENTITY": "<XETE_IDENTITY>",
        "XETE_SOL_KEYPAIR": "<XETE_SOL_KEYPAIR>",
        "XETE_PERMIT_URL": "<XETE_PERMIT_URL>",
        "XETE_SOLANA_RPC": "<XETE_SOLANA_RPC>",
        "XETE_SPEND_MAX_LAMPORTS": "<XETE_SPEND_MAX_LAMPORTS>",
        "XETE_SPEND_WINDOW_LAMPORTS": "<XETE_SPEND_WINDOW_LAMPORTS>",
        "XETE_SPEND_WINDOW_SECONDS": "<XETE_SPEND_WINDOW_SECONDS>",
        "XETE_SPEND_FLOOR_LAMPORTS": "<XETE_SPEND_FLOOR_LAMPORTS>",
        "XETE_SPEND_LEDGER": "<XETE_SPEND_LEDGER>"
      }
    }
  }
}

Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs

xete in other clients

xete MCP server