hush
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., "@hushCheck if MY_API_KEY is available; if not, ask me for it."
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.
hush — AI agents use secrets without ever seeing them
npm i -g --allow-scripts=hush-secrets hush-secrets # installs binary + skill
hush set MY_API_KEY # in YOUR terminal, never in chat
hush update # self-update from GitHub releasesWhy
Pasting a secret into a harness chat leaves it in the transcript forever.
hush separates the channels: the human loads values via TTY or the harness
native prompt (over MCP), the agent only orchestrates names. No tool ever
returns a value.
Related MCP server: keyper
MCP (harness-agnostic: claude, opencode, cursor, codex)
hush serve exposes stdio with 4 tools: hush_check, hush_list, hush_need
(asks for the value via elicitation and stores it), hush_run (injects +
redacts). hush setup installs the skill and shows how to register the
server in each harness.
CLI
openssl rand -hex 24 | hush set WHATSAPP_VERIFY_TOKEN
hush check WHATSAPP_VERIFY_TOKEN META_APP_SECRET
hush stdin WHATSAPP_VERIFY_TOKEN -- npx wrangler secret put WHATSAPP_VERIFY_TOKEN
hush run --only META_APP_SECRET -- npx wrangler deploy
hush statuscheck and list print names only. run and stdin inject into the child
process and redact output to [REDACTED].
Where secrets live, and getting them back
Values are stored in ~/.hush/vault (file 0600, dir 0700), one
NAME=value per line. There is intentionally no read-back over MCP and
no get command — anything an agent can call ends up in its context.
To recover a value (rotation, migration, backup), use a real terminal:
hush export # prints all, NAME=value per line
hush export META_APP_SECRET # prints oneexport refuses to run unless stdout is a TTY, so no harness can capture it
by piping. Back up the file itself (cp ~/.hush/vault …) for disaster
recovery; wipe with rm -rf ~/.hush. See SECURITY.md and PRIVACY.md.
Docs
SECURITY.md (threat model) · PRIVACY.md · CONTRIBUTING.md · CHANGELOG.md
Alternatives
hush | psst | key-amnesia | akm | 1Password MCP | |
Agent never sees values | ✅ | ✅ | ✅ | ✅ | ✅ |
MCP server | ✅ | ❌ | ❌ | ❌ | ✅ (Codex only) |
Load via native prompt (no chat) | ✅ elicitation | ❌ | ✅ popup | ❌ | ✅ |
TTY-only export | ✅ | ❌ | ❌ | ❌ | ❌ |
Vault corruption guard | ✅ | n/a | ❌ | ❌ | n/a |
Harness-agnostic setup | ✅ | ❌ | parcial | ❌ | ❌ |
Single binary, no runtime | ✅ Go | ✅ | ❌ Python | ✅ Rust* | ❌ |
Works offline / local-only | ✅ | ✅ | ✅ | ✅ | ❌ |
*akm is macOS-only (Keychain). hush keeps a plain 0600 file so any dev can
inspect, back up, and recover it with standard tools.
Development
make check # generate + fmt + vet + test + build
make hook # pre-commit (generate + fmt + vet + test)
./scripts/release.sh 0.2.0 # bump + tag (workflow publishes npm + release)Conventional commits: feat:, fix:, chore:, docs:, refactor:, test:.
SKILL.md is the single source of the skill; internal/setup/skill.md is
regenerated with go generate ./... (a test enforces it).
This server cannot be deployed
Maintenance
Related MCP Connectors
A secret store for AI agents: the agent never sees the plaintext.
Secrets for developers and agents—secure context and workflows without exposing secret values.
Encrypted secret store and rotation for autonomous agent credentials
- TAPOAuthtech.human
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to securely use secrets by running commands with environment-injected credentials and sanitizing output to prevent leakage.1-
- AlicenseNot gradedqualityCmaintenanceEncrypts and stores API keys and environment variables locally, providing them to AI agents via MCP with tools for listing, describing, getting secrets, and running commands with secret values redacted.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to securely use API keys by storing them in an encrypted vault and injecting them on demand with user approval, without exposing the key values to the model.1MIT
- AlicenseNot gradedqualityBmaintenanceSecure, encrypted API key management for AI coding agents, enabling search, inspection, and use of credentials with scoped permissions and optional zero-knowledge decryption.MIT