Encrypted secrets vault for AI agents — secrets resolved at runtime, never seen by LLMs.
If you already use Keyblind, the keyblind mcp server is the piece that lets your assistant work with it directly. Encrypted secrets vault for AI agents — secrets resolved at runtime, never seen by LLMs.
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.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
resolve_secret — Resolve a secret at runtime (value hidden from transcript)store_secret — Encrypt and store a secretlist_secrets — List secret names (values never revealed)delete_secret — Delete a secretsandbox_env — Replace .env values with deterministic fakesunsandbox_env — Restore real .env values from vaultaudit_log — View secret resolution audit trailtotp_code — Generate a TOTP 2FA code for a stored configtotp_store — Store a TOTP configuration from otpauth:// URItotp_list — List all stored TOTP configurationstotp_delete — Delete a TOTP configurationcreate_share_link — Create encrypted, expiring share link for a secretConfiguration is passed through the environment: OPENAI_API_KEY, DATABASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Installation goes through your MCP client rather than a global install: point it at keyblind on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Keyblind's toolset — resolve_secret, store_secret, list_secrets and 11 more — is a fair guide to whether it matches your workflow. It is maintained by aarifmms; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| 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) |
| delete_secret | Delete a secret |
| sandbox_env | Replace .env values with deterministic fakes |
| unsandbox_env | Restore real .env values from vault |
| audit_log | View secret resolution audit trail |
| totp_code | Generate a TOTP 2FA code for a stored config |
| totp_store | Store a TOTP configuration from otpauth:// URI |
| totp_list | List all stored TOTP configurations |
| totp_delete | Delete a TOTP configuration |
| create_share_link | Create encrypted, expiring share link for a secret |
| receive_share | Receive and decrypt a shared secret |
| deadman_status | Check dead man's switch status |
{
"mcpServers": {
"keyblind": {
"command": "npx",
"args": ["-y", "keyblind"],
"env": {
"OPENAI_API_KEY": "your-value",
"DATABASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| DATABASE_URL | Endpoint or connection string the server talks to. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.