mcpField
E
envibe

envibe

Local
github.com/dominic-righthereSecurity0Updated 38w ago
Repository

About envibe

envibe-mcp is an MCP server that gives AI coding assistants permission-controlled access to environment variables. Its access levels determine what the AI can view or modify, while setup generates a manifest and filtered .env.ai file and blocks direct .env access.

Key features

  1. 01Five variable access levels
  2. 02List and retrieve permitted variables
  3. 03Set variables with full access
  4. 04Describe variable formats and examples
  5. 05Check missing required variables
  6. 06Block direct .env access

Use cases

  1. 01Limit an assistant's visibility of secrets
  2. 02Allow selected environment variables to be edited
  3. 03Guide setup of required variables
  4. 04Provide format hints for configuration

MCP support

envibe-mcp exposes tools for listing, reading, setting, and describing environment variables, and checking required variables. AI clients can connect to it through their MCP configuration.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "dominic-righthere-envibe": {
      "command": "npx",
      "args": [
        "-y",
        "envibe-mcp"
      ]
    }
  }
}
Run commandnpx -y envibe-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmenvibe-mcp0.2.7

Tools

6

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

envibe-mcp

npm version License: MIT

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

Install

Add to your AI tool's MCP config:

{
  "mcpServers": {
    "envibe": {
      "command": "npx",
      "args": ["envibe-mcp"]
    }
  }
}
Claude Code 
claude mcp add envibe npx envibe-mcp
Claude Desktop

Add to claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
VS Code / Cursor / Windsurf

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

On first run, envibe automatically:

  1. Creates .env.manifest.yaml from your .env.example
  2. Generates .env.ai (filtered view for AI)
  3. Blocks direct .env file access

What is this?

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

LevelAI Can SeeAI Can Modify
fullActual valueYes
read-onlyActual valueNo
placeholder<VAR_NAME>No
schema-onlyFormat onlyNo
hiddenNothingNo

MCP Tools

ToolDescription
env_listList visible variables with access levels
env_getGet a variable's value (respects permissions)
env_setSet a variable (only full access)
env_describeGet detailed info including format and example
env_check_requiredCheck which required variables are missing
v0.2.0 Features
  • 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

For CLI tools

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

npm install -g envibe

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.