Envibe MCP
E

Envibe MCP

The MCP server component of the envibe project, providing controlled.env environment variable access permission management for AI assistants
2 points
5.1K

What is Envibe MCP Server?

Envibe MCP Server is an intelligent permission management system that establishes a security layer between AI assistants (such as Claude, Cursor, etc.) and your environment configuration files (.env files). It allows AI to see and use necessary environment variables while protecting sensitive information from being leaked.

How to use Envibe MCP Server?

Simply add the Envibe MCP server to your AI tool configuration, and it will automatically create a permission configuration file and control the AI's access to environment variables based on the preset access levels. When running for the first time, the system will automatically scan your environment configuration files and set the corresponding permissions.

Applicable scenarios

When you want an AI assistant to help with development, debugging, or application configuration but don't want the AI to directly access environment variables containing sensitive information such as API keys and database passwords, Envibe is the ideal choice. It is particularly suitable for team collaboration, open - source projects, or situations where you need to share the development environment with AI.

Main features

5 - level fine - grained permission control
Provide 5 different permission levels from full access to complete hiding, allowing you to precisely control which environment variables the AI can see and modify.
Automatic configuration wizard
Automatically create a permission inventory from.env.example during the first run, generate an AI - specific view file, and prevent direct access to the original.env file.
4 MCP tool sets
Provide dedicated tools such as env_list, env_get, env_set, env_describe, and env_check_required, enabling the AI to interact with environment variables securely.
Intelligent error prompts
When the AI attempts to access restricted variables, provide clear error messages and operation instructions to help users understand the permission limitations.
Format hint system
Display the expected format of environment variables (URL, key, number, etc.) to help the AI correctly understand and use the variables.
Required variable check
The env_check_required tool can identify missing required environment variables and guide users to complete the full configuration.
Advantages
High security: Protect sensitive information from being accidentally leaked by AI
Simple configuration: One - click installation and automatic initialization
Flexible control: 5 permission levels meet different security requirements
Development - friendly: AI can still assist in development without affecting work efficiency
Error - friendly: Clear permission error prompts and guidance
Limitations
Requires additional configuration: Need to add MCP server configuration in AI tools
Learning curve: Need to understand the differences between 5 permission levels
Depends on MCP protocol: Only applicable to AI tools that support MCP
Initial setup: Need to create a permission configuration file when using for the first time

How to use

Installation and configuration
Add the Envibe MCP server to the configuration file of the AI tool you are using. The configuration method varies slightly depending on different AI tools (Claude Desktop, VS Code, Cursor, etc.).
First run
After starting the AI tool, Envibe will automatically scan your project, create a permission configuration file, and set the initial permissions. The system will generate a.manifest.yaml file based on.env.example.
Permission configuration
Edit the.env.manifest.yaml file to set appropriate access levels for each environment variable. There are 5 levels to choose from: full, read - only, placeholder, schema - only, hidden.
Start using
Now the AI assistant can safely access environment variables through MCP tools. The AI can only see and modify the variables you allow, and sensitive information is protected.

Usage cases

Securely configure API keys
You want the AI to help set up a new Stripe API key, but don't want the AI to see other sensitive keys. Set the STRIPE_API_KEY to 'full' permission and other keys to 'hidden'.
Check missing configurations
A new team member joins the project and needs to configure all required environment variables. Use the env_check_required tool to identify the missing items.
Debug database connection issues
The AI needs to help debug database connection issues, but you don't want to expose the real database password. Set the DATABASE_URL to 'placeholder' permission.

Frequently Asked Questions

What are the differences between the 5 permission levels?
Will Envibe affect my normal development?
How to update the permission configuration?
What if the AI needs to access a hidden variable?
Which AI tools are supported?
How to install the complete CLI tool?

Related resources

Envibe GitHub repository
The complete source code and detailed documentation of the Envibe project
MCP protocol official documentation
The official specification and documentation of the Model Context Protocol
npm package page
The npm package information and version history of Envibe MCP Server
Claude Desktop configuration guide
The official guide for configuring the MCP server in Claude Desktop

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "envibe": {
      "command": "npx",
      "args": ["envibe-mcp"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
15.2K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
14.5K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
21.2K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
12.6K
4 points
P
Paperbanana
Python
13.2K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
14.3K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
13.5K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
15.2K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
44.2K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
28.6K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
33.4K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
95.9K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
79.9K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
42.8K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
28.6K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
67.6K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase