Manage encrypted environment variables with AI-safe access policies, preventing AI agents from reading secrets they shouldn't need. Developers use it to keep sensitive credentials isolated while letting Claude and other AI tools access only approved variables.
io.github.fentz26/envcp
Local install
STDIO
No auth required
How models use it and what it is built for.
Manage encrypted environment variables with AI-safe access policies, preventing AI agents from reading secrets they shouldn't need. Developers use it to keep sensitive credentials isolated while letting Claude and other AI tools access only approved variables.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Fentz26 Envcp.
Paste any of these into Agent Studio after connecting Fentz26 Envcp.
Common questions about connecting and running Fentz26 Envcp.
What problem does envcp solve?
It prevents AI agents from reading environment variables they don't need by enforcing granular access policies. Secrets stay encrypted and isolated, reducing the risk of accidental exposure when running AI-assisted code.
How do I install and set up envcp?
Install with `npx @fentz26/envcp@1.0.82`. The MCP server runs over stdio and integrates with your AI chat client to enforce access policies on environment variables at runtime.
Can I use envcp with Claude or other AI models?
Yes—envcp is designed as an MCP server specifically to work with AI agents like Claude. It lets you define which variables each AI session can access before connecting.
How are secrets encrypted in envcp?
The registry metadata doesn't specify the encryption algorithm. Check the project repository or documentation for details on key derivation, cipher choice, and storage format.
What's the difference between envcp and a standard .env file?
Standard .env files are plaintext and give AI agents access to all variables. envcp encrypts secrets and enforces per-agent access policies, so you can safely share code with AI without exposing sensitive credentials.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams