Enables encrypting files and text using GitHub usernames, allowing for secure content sharing based on GitHub identities.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SAFE MCP Server Encrypt secret_notes.txt for github:username"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that gives AI assistants the ability to encrypt and decrypt files using SAFE.
The safe CLI must be installed and available in PATH. See thesafe.dev/download.
Related MCP server: Files MCP Server
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"safe-encryption": {
"command": "npx",
"args": ["safe-mcp-server"]
}
}
}Add to .cursor/mcp.json:
{
"mcpServers": {
"safe-encryption": {
"command": "npx",
"args": ["safe-mcp-server"]
}
}
}Tool | Description |
| Encrypt text or file with password, public key, or GitHub username |
| Decrypt a .safe file (auto-discovers keys from ~/.safe/ and ~/.ssh/) |
| Generate encryption keypair (x25519, p-256, ml-kem-768) |
| Inspect encrypted file metadata without decrypting |
| List identities and recipients |
Once configured, ask your AI assistant:
"Encrypt this file with a password"
"Decrypt secrets.safe"
"Generate an encryption key"
"Encrypt this for github:alice"
"Who can decrypt this .safe file?"
This server cannot be deployed
Discover, invoke, and trustlessly verify ForceDream AI agents with cryptographic proofs. 17 tools.
Encrypted secret store and rotation for autonomous agent credentials
Encrypted A2A object storage for autonomous agent state and artifacts
Securely search and manage workspace context files for AI agents and teams.