Secret Safe Env
A Windows-only server that writes secrets to .env files without exposing them to the agent or chat context. Instead of pasting API keys into the conversation, the agent calls set_env_secret with just the variable name, which opens a native masked WinForms dialog where you type the value. The secret travels straight from your keyboard to PowerShell to the file, bypassing command line args, PSReadLine history, script block logging, and the model context entirely. Includes env_key_exists to confirm writes without reading values back out. Built specifically to close the leak that happens when you hand credentials to an agent inline or verify them with cat .env. The UI is in Traditional Chinese, but the tools work with standard English key names.
- tools
- 2
- transport
- STDIO
- last updated
- Jun 6, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
set_env_secretOpens the masked dialog for `key`; the user types the value; the helper writes `key=value` to `.env`. Returns human/agent-readable text plus an error flag — never the value.
Opens the masked dialog for `key`; the user types the value; the helper writes `key=value` to `.env`. Returns human/agent-readable text plus an error flag — never the value.
No parameter schema in public metadata yet.
env_key_existsReturns only whether `key` is present in `.env` — never the value. Use it to confirm a write instead of reading/`cat`-ing `.env`.
Returns only whether `key` is present in `.env` — never the value. Use it to confirm a write instead of reading/`cat`-ing `.env`.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
secret-safe-env
A Model Context Protocol server that lets an AI agent put a secret (API key, token, password, connection string) into a project's .env file without the agent ever seeing the value.
The agent calls a tool with only the variable name. A native, masked Windows dialog opens locally; you type the value; a local PowerShell helper writes it straight to .env. The agent receives only a status token (OK / CANCEL / ERR:<CODE>) — never the secret.
繁體中文說明見 README.zh-TW.md.
Demo
Details
- Repository
- github.com/irrenwill/secret-safe-env
- Category
- AI & LLM Tools
- Package
secret-safe-env- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
ForgingStack Quorumjdkabattles/forgingstack-quorumBefore an agent acts alone, get the quorum. One proposal, N approvals, one receipt.0starsForgingStack Watchtowerjdkabattles/forgingstack-watchtowerAn agent that stops checking in is an agent you hear about.0stars
Consentgate Mcpjessepetersondev/consentgate-mcpGate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.0stars
Codex Imagesjlmoreno00/codex-images-mcpGenerate and edit images with gpt-image-2, including masks and transparency.0stars