AIBase
EN
Explore
Lex
L

Lex

Lex is a TypeScript framework that provides situational memory and architecture awareness for AI agents, solving the problem of context loss in long - process development. Through memory snapshots, module dependency navigation, and architecture policy execution, it enables AI assistants to remember work progress and understand code structure.
Knowledge management and memoryDeveloper tools#AI memory framework#Architecture awareness#Policy execution#MCP integration.TypeScript
2 points
5.5K
Open Site

Overview

Installation

Content Details

Alternatives

What is Lex MCP Server?

Lex MCP Server is a server based on the Model Context Protocol (MCP), which exposes the memory and architecture awareness functions of the Lex framework to AI assistants. Through this server, AI assistants (such as Claude Desktop, Cursor, etc.) can access your work memory, code architecture information, and development specifications. In simple terms, it allows AI assistants to: - Remember what work you've done before - Understand the structure of your codebase - Know which code can be modified and which cannot - Adhere to the development specifications set by the team

How to use Lex MCP Server?

Using Lex MCP Server is very simple and only requires three steps: 1. Install the Lex MCP package 2. Configure your AI assistant (VS Code or Claude Desktop) 3. Start a conversation with the AI assistant with memory After the server starts, the AI assistant will automatically gain 11 new tools, including memory search, architecture analysis, policy check, etc.

Use cases

Lex MCP Server is particularly suitable for the following scenarios: - Long - term development projects: AI assistants can remember work done days or even weeks ago - Complex codebases: AI assistants can understand module dependencies - Team collaboration: Ensure that AI assistants adhere to team specifications - Onboarding of new team members: Quickly understand the project through historical memory - Architecture refactoring: AI assistants know which modules can be safely modified

Main features

Memory management tools
Provide complete memory lifecycle management: create new memories, search historical memories, retrieve specific memories, list all memories, and verify memory formats. AI assistants can remember and recall work content like humans.
Architecture policy check
Check in real - time whether code modifications violate architecture specifications. AI assistants will check policies before suggesting modifications to prevent introducing architecture violations.
Architecture analysis
Analyze the dependencies and architecture context of code modules. AI assistants can understand the structure of the codebase and provide more accurate suggestions.
Timeline view
Visually display the development history of the project. AI assistants can see the evolution process of the work and understand why certain decisions were made.
System self - check
Check the server status and configuration. Ensure that the MCP server runs normally and detect configuration issues in a timely manner.
Help and tips
Provide usage guidance and context tips. Help users and AI assistants make better use of Lex's functions.
Advantages
Seamless integration: Seamlessly integrate with mainstream AI assistants (Claude Desktop, Cursor, etc.)
Zero - configuration memory: AI assistants automatically gain memory capabilities without additional configuration
Architecture security: Prevent AI assistants from violating important architecture specifications
Rich context: Provide accurate code context for AI assistants to avoid information overload
Cross - session persistence: Memories are retained after the AI assistant restarts
Standardized interface: Use the MCP standard protocol with good compatibility
Limitations
Requires a Node.js environment: The server needs Node.js 20+ to run
Initial configuration: Simple configuration steps are required for the first use
Text - only: Currently mainly handles text memories and does not support binary files
Depends on the Lex framework: The Lex framework needs to be installed first to use
Learning curve: Basic concepts of memory and policies need to be understood

How to use

Install the Lex MCP package
First, install the Lex MCP server package. You can choose to install it globally or run it directly using npx.
Configure VS Code
If you use VS Code, you need to create a.vscode/mcp.json configuration file in the project root directory.
Configure Claude Desktop
If you use Claude Desktop, you need to edit its configuration file to add the MCP server.
Start and use
After the configuration is completed, restart your AI assistant. Now the AI assistant can use all of Lex's tools.

Usage examples

Continue interrupted work
You were interrupted while implementing the user login function yesterday. When you come back today, the AI assistant can immediately recall yesterday's progress.
Refactor code safely
You want the AI assistant to help refactor the payment processing module but are worried that it doesn't know the architecture constraints.
Understand project history
You're new to the project and want to understand why a certain feature is implemented in a certain way.
Check architecture compliance
Before submitting the code, let the AI assistant check if there are any architecture violations.

Frequently Asked Questions

What's the difference between Lex MCP Server and Lex CLI?
Do I need to install both the Lex framework and Lex MCP?
Will the MCP server affect the response speed of the AI assistant?
Where is the memory data stored? Is it secure?
Can multiple AI assistants share the same memory?
What if the MCP server crashes?
Which AI assistants are supported?
How to update the architecture policy?

Related resources

Lex framework documentation
Complete documentation of the Lex framework, including installation, configuration, and usage guides
Model Context Protocol official website
Official documentation and specifications of the MCP protocol
Lex MCP npm package
npm package page of the Lex MCP Server
Example configuration files
Examples of various configuration files
Problem feedback
Report bugs or propose feature suggestions

Installation

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

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
16.2K
5 points
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
9.5K
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
10.1K
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
14.8K
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
6.7K
4 points
P
Paperbanana
Python
8.9K
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
8.7K
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
10.0K
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
24.8K
4.5 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
38.1K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
80.3K
4.3 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
28.5K
4.3 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#
38.4K
5 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
69.6K
4.5 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
24.0K
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
56.4K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2026AIBase