Keyblind

Keyblind — Blind AI to Your Keys

Encrypted secrets vault with MCP for AI agents. One command configures every editor. Secrets resolved at runtime, never leaked to LLM conversations.

Why

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.

How It Works

┌──────────┐     ┌────────────────┐     ┌─────────────────┐

│ AI Agent │ ──→ │ Keyblind MCP │ ──→ │ Encrypted │ │ (Claude) │ │ Server │ │ SQLite Vault │ │ │ ←── │ (27 tools) │ ←── │ (AES-256-GCM) │ └──────────┘ └────────────────┘ └─────────────────┘ ↑ │ │ secret value never appears │ secrets never │ in conversation transcript │ stored in plaintext

Quick Start

# 1. Install

npm i -g keyblind

2. One-command setup (initialize vault + configure Claude Code)

keyblind quickstart

3. Store secrets

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

4. Sandbox your .env (AI agents see fakes)

keyblind sandbox

5. Resolve a secret

keyblind get OPENAI_API_KEY

6. Run commands with secrets injected as env vars

keyblind run -- npm start

7. List all secrets (names only, values hidden)

keyblind list

That's it. After keyblind quickstart, restart Claude Code. Then just say _"list my keyblind secrets"_ or _"use my OPENAI_API_KEY"_ — the AI agent resolves secrets at runtime without ever seeing them in the transcript.

MCP Server

Keyblind is MCP-first — it works with every AI tool that speaks the Model Context Protocol (Claude Code, Cursor, Copilot, Windsurf, Cline, Zed).

Setup (automatic)

keyblind setup-mcp

This auto-configures Claude Code, Cline, and Zed to use Keyblind. Works from any directory.

For project-local editors (Cursor, Windsurf, Copilot, Cline project mode), run from your project root:

keyblind setup-mcp --local

See editor-specific configs for details and manual setup.

Setup (manual)

Add a .mcp.json to your project root, or use claude mcp add:

claude mcp add --scope user keyblind -- keyblind start

With biometric gate (Touch ID required before secrets are resolved):

keyblind unlock                      # Authenticate first

claude mcp add keyblind -- keyblind start --biometric

Session expires after 15 minutes. Requires Pro or Team license.

MCP Tools

Web Dashboard

Manage your secrets from a browser — no sign-in or pairing required. Open the local dashboard:

keyblind dashboard

This starts the local server and opens http://localhost:4318/ in your browser. The dashboard is served same-origin with the REST API, so it works in every browser with no CORS, no pairing token, and no login. Features:

• View, add, copy, and delete secrets
• Audit log with full access history
• License management (tier, email, expiry)
• Pro/Team tier status
• Per-secret access policies and rotation reminders
• Agent action approvals (approve/deny queued agent writes)
• Central control plane (org-wide visibility + signed revocation)

A hosted control plane (hosted/) adds orgs, roles, groups, a signed revocation + group-scope manifest, multi-provider SSO login (with org auto-provisioning, multi-org switching, and IdP end-session revocation), and short-lived agent credentials. See docs/enterprise.md (Phase 2).

Browser Extension

The Keyblind Chrome Extension detects and blocks secrets from being pasted into AI chat interfaces (Claude.ai, ChatGPT, Copilot).

Features:

• Detects 12+ API key formats (OpenAI, GitHub, Stripe, AWS, etc.)
• Intercepts paste events on AI chat sites
• Warning banner when secrets are detected
• Popup with vault connection status

Located in browser-extension/. Load as unpacked extension from chrome://extensions.

Pricing

# Buy a license at keyblind.dev, then activate:

keyblind activate

Check your status

keyblind status

Backends

Keyblind supports multiple secret backends:

keyblind backends                          # List available backends

keyblind backend 1password # Switch to 1Password keyblind backend bitwarden # Switch to Bitwarden

Keyblind vs Cloak

Security

• 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 `~/.keyblind/` with 0700 permissions
• Deterministic sandbox fakes using HMAC-SHA256 per project + key name

Verifying Your Install

Releases are built and published from GitHub Actions with npm provenance, which attests the tarball was produced from this repository's CI rather than a developer machine.

npm audit signatures        # Verify npm registry signatures

To verify build provenance for a release, open the release page at https://github.com/aarifmms/keyblind/releases and check the "Provenance" and "Attestations" sections, which link the tarball to the exact commit and workflow run that built it.

• Small dependency graph — the CLI depends on three packages only (MCP SDK, better-sqlite3, zod). Server-only deps (Stripe, Resend, the Vercel CLI) live in the hosted/ and dashboard/ packages and are not installed by npm i -g keyblind.
• No source maps — the published tarball ships compiled JavaScript with no embedded original source.

CLI Reference

keyblind quickstart           One-command setup (init + configure Claude Code)

keyblind init Initialize the encrypted vault keyblind set Store a secret (value from stdin) keyblind set - Store a secret (prompts securely) keyblind get Resolve and print a secret keyblind list List all stored secrets keyblind delete Delete a secret keyblind setup-mcp Auto-configure MCP for Claude Code, Cline, Zed keyblind setup-mcp --local Write project MCP configs (Cursor, Windsurf, Copilot, Cline) keyblind sandbox [.env] Replace .env with deterministic fakes keyblind unsandbox [.env] Restore real .env values keyblind run Run command with secrets as env vars keyblind start Start MCP server (stdio — for AI agents) keyblind start --http Start HTTP server (dashboard + MCP + REST API) keyblind dashboard Open the web dashboard in your browser keyblind start --biometric Start MCP server with biometric requirement keyblind backends List available backends keyblind backend Switch backend keyblind activate Activate a Pro/Team license keyblind deactivate Remove current license keyblind status Show license and vault status keyblind audit Show secret resolution audit log keyblind check --expired List secrets past expiry keyblind rotate Update a secret value keyblind rotate --generate Rotate with an auto-generated value keyblind rotate --exec " " Rotate via an external command's stdout keyblind rotate --overdue [days] Rotate all secrets past the threshold keyblind rotate-needed [days] List secrets not rotated in N days (default 90) keyblind agents list List registered AI agents keyblind agents register [scope] Register an agent (prints signing key) keyblind agents verify Verify agent ledger integrity keyblind agents export [json|csv] Export compliance report keyblind agents