io.github.dominic-righthere/envibe

Official

by dominic-righthere · TypeScript

Secure permission layer between AI agents and your .env files

Secure permission layer controlling AI agent access to environment variable files.

Topics

ai-agentsmcpmodel-context-protocoltypescript

MCP server for envibe - the missing permission layer between AI agents and your .env.

Add to your AI tool's MCP config:

json

{
  "mcpServers": {
    "envibe": {
      "command": "npx",
      "args": ["envibe-mcp"]
    }
  }
}

<details> <summary>Claude Code</summary>

bash

claude mcp add envibe npx envibe-mcp

</details> <details> <summary>Claude Desktop</summary>

Add to claude_desktop_config.json:

</details> <details> <summary>VS Code / Cursor / Windsurf</summary>

Add to your editor's MCP settings (see main envibe docs for details).

</details>

On first run, envibe automatically:

This is the MCP server component of envibe. It gives AI coding assistants controlled access to your environment variables with 5 access levels:

Tool	Description
`env_list`	List visible variables with access levels
`env_get`	Get a variable's value (respects permissions)
`env_set`	Set a variable (only `full` access)
`env_describe`	Get detailed info including format and example
`env_check_required`	Check which required variables are missing

Better error messages - When access is denied, get helpful guidance
Format hints - Know what format a variable should be (url, key, number, etc.)
Required var checking - Use env_check_required to guide users through setup

If you need CLI commands like envibe setup -i (interactive mode), envibe view, or envibe generate, install the full package:

bash

npm install -g envibe

MIT

claude_desktop_config.json

{
  "mcpServers": {
    "envibe": {
      "command": "npx",
      "args": [
        "-y",
        "envibe-mcp@0.2.7"
      ]
    }
  }
}