cd /news/ai-safety/keyblind-encrypted-secrets-vault-tha… · home topics ai-safety article
[ARTICLE · art-14672] src=github.com pub= topic=ai-safety verified=true sentiment=↑ positive

Keyblind – encrypted secrets vault that hides API keys from AI agents

Keyblind launched an encrypted secrets vault that prevents AI agents from exposing API keys, passwords, and tokens during coding sessions. The tool resolves secrets at runtime so plaintext values never appear in LLM conversation transcripts, addressing the 100,000+ leaked credentials found indexed by search engines in 2025. Keyblind integrates with any MCP-compatible editor including Claude Code, Cursor, and Copilot, and supports local SQLite, 1Password, and Bitwarden backends with zero network traffic.

read3 min publishedMay 26, 2026

Encrypted secrets vault with MCP for AI agents. Secrets resolved at runtime, never leaked to LLM conversations.

Developers regularly leak API keys, passwords, and tokens to AI coding tools. 100,000+ LLM conversations with exposed secrets were found indexed by search engines in 2025.

AI agents read your .env

files. They copy-paste secrets into conversations. They commit them accidentally. Keyblind stops this by keeping secrets encrypted at rest and resolving them at runtime — the plaintext value never touches the LLM transcript.

┌──────────┐     ┌────────────────┐     ┌─────────────────┐
│ AI Agent │ ──→ │  Keyblind MCP  │ ──→ │  Encrypted      │
│ (Claude) │     │  Server        │     │  SQLite Vault   │
│          │ ←── │  (6 tools)     │ ←── │  (AES-256-GCM)  │
└──────────┘     └────────────────┘     └─────────────────┘
      ↑                                        │
      │ secret value never appears             │ secrets never
      │ in conversation transcript             │ stored in plaintext
npm i -g keyblind

keyblind init

echo "sk-proj-abc123" | keyblind set OPENAI_API_KEY
keyblind set DATABASE_URL -    # prompts securely

keyblind sandbox

keyblind get OPENAI_API_KEY

keyblind run -- npm start

keyblind list

Keyblind is MCP-first — it works with every AI tool that speaks the Model Context Protocol:

Claude Code — add to .mcp.json

:

{
  "mcpServers": {
    "keyblind": {
      "command": "npx",
      "args": ["keyblind", "start"]
    }
  }
}

Cursor, Windsurf, Copilot, Cline, Zed — any MCP-compatible editor.

Tool Description
resolve_secret
Resolve a secret at runtime (value hidden from transcript)
store_secret
Encrypt and store a secret
list_secrets
List secret names (values never revealed)
sandbox_env
Replace .env values with deterministic fakes
unsandbox_env
Restore real .env values from vault
delete_secret
Delete a secret

Keyblind supports multiple secret backends:

keyblind backends                          # List available backends
keyblind backend 1password                 # Switch to 1Password
keyblind backend bitwarden                 # Switch to Bitwarden
Backend Read Write Requires
local (default)
Nothing
1password
op CLI
bitwarden
bw CLI
env
Nothing
Keyblind Cloak
Protocol
MCP (all editors) VS Code extension only
Storage
AES-256-GCM SQLite AES-256-GCM file
Backends
Local, 1Password, Bitwarden, Env Local only
Sandbox
Deterministic HMAC fakes AES-256-GCM encrypted
Touch ID
✓ (macOS biometric gate)
CI/CD
keyblind run for env injection
Network
Zero (fully local) Zero
License
MIT Proprietary

AES-256-GCM encryption with PBKDF2 key derivation (600K iterations)Machine-identity-bound key— encryption key XOR-wrapped with machine fingerprint** Zero network, zero telemetry**— no cloud, no accounts, no analytics** Vault stored at**with~/.keyblind/

0700

permissionsDeterministic sandbox fakes using HMAC-SHA256 per project + key name

keyblind init                 Initialize the encrypted vault
keyblind set <name>           Store a secret (value from stdin)
keyblind set <name> -         Store a secret (prompts securely)
keyblind get <name>           Resolve and print a secret
keyblind list                 List all stored secrets
keyblind delete <name>        Delete a secret
keyblind sandbox [.env]       Replace .env with deterministic fakes
keyblind unsandbox [.env]     Restore real .env values
keyblind run <command...>     Run command with secrets as env vars
keyblind start                Start MCP server (for AI agents)
keyblind backends             List available backends
keyblind backend <name>       Switch backend
git clone https://github.com/aarifmms/keyblind.git
cd keyblind
npm install
npm run build       # Compile TypeScript
npm test            # Run tests
npm run dev         # Watch mode

MIT

── more in #ai-safety 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/keyblind-encrypted-s…] indexed:0 read:3min 2026-05-26 ·