LAD MCP Server
Lad MCP Server: Autonomous code & system design review for AI coding agents (Claude Code, Cursor, Codex, etc.). Features multi-model consensus via OpenRouter and context-aware reviews via Serena.
What is LAD MCP Server?
LAD MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to lad mcp server: autonomous code & system design review for ai coding agents (claude code, cursor, codex, etc.). features multi-model consensus via openrouter and context-aware reviews via serena.
Lad MCP Server: Autonomous code & system design review for AI coding agents (Claude Code, Cursor, Codex, etc.). Features multi-model consensus via OpenRouter and context-aware reviews via Serena.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Lad MCP Server: Autonomous code & system design review for A
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx lad-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LAD MCP Server
LAD MCP Server is a Python-based autonomous code and system design review tool for AI coding agents (Claude Code, Cursor, Codex, and similar). It exposes two MCP tools — 'code_review' and 'system_design_review' — that run two OpenRouter-backed language models in parallel and synthesize their assessments into a single consensus report. Optional integration with the Serena MCP server provides long-term codebase memory and project-aware context, making reviews more accurate over time. Engineering teams use it to add an independent AI review layer to their agent-driven development workflows.
Prerequisites
- Python 3.10 or later and 'uv' or 'uvx' installed
- An OpenRouter API key (get one at openrouter.ai)
- An MCP-compatible client such as Claude Desktop, Claude Code, or Cursor
- Optional: the Serena MCP server for context-aware reviews with codebase memory
Get an OpenRouter API key
Sign up at openrouter.ai and create an API key. The server uses OpenRouter to access multiple LLMs (default: Kimi K2.5 as primary and MiniMax M2.7 as secondary reviewer).
Run the server with uvx (recommended)
Install and run the server directly from the GitHub repository using uvx — no local clone required.
uvx --from git+https://github.com/Shelpuk-AI-Technology-Consulting/lad_mcp_server lad-mcp-serverAdd the server to your MCP client configuration
Add the LAD MCP server entry to your claude_desktop_config.json with your OpenRouter API key.
{
"mcpServers": {
"lad": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Shelpuk-AI-Technology-Consulting/lad_mcp_server",
"lad-mcp-server"
],
"env": {
"OPENROUTER_API_KEY": "sk-or-v1-xxxxxxxxxxxx"
}
}
}
}Optionally customize reviewer models
Override the default primary and secondary reviewer models using environment variables. Set the secondary to '0' for single-reviewer mode.
# In your MCP env config or shell:
OPENROUTER_PRIMARY_REVIEWER_MODEL=moonshotai/kimi-k2.5
OPENROUTER_SECONDARY_REVIEWER_MODEL=minimax/minimax-m2.7
OPENROUTER_REVIEWER_TIMEOUT_SECONDS=300
OPENROUTER_FIXED_OUTPUT_TOKENS=8192Restart your MCP client and test
Restart Claude Desktop or Claude Code and ask it to review a code file. The tool accepts file paths, directory paths, or inline code text.
LAD MCP Server Examples
Client configuration
claude_desktop_config.json entry for LAD MCP server with OpenRouter.
{
"mcpServers": {
"lad": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Shelpuk-AI-Technology-Consulting/lad_mcp_server",
"lad-mcp-server"
],
"env": {
"OPENROUTER_API_KEY": "sk-or-v1-xxxxxxxxxxxx",
"OPENROUTER_PRIMARY_REVIEWER_MODEL": "moonshotai/kimi-k2.5",
"OPENROUTER_SECONDARY_REVIEWER_MODEL": "minimax/minimax-m2.7"
}
}
}
}Prompts to try
Example prompts for invoking code review and system design review via Claude.
- "Use the LAD code_review tool to review /Users/me/project/src/api.py and give me a consensus assessment."
- "Review the system design in /Users/me/project/ARCHITECTURE.md for scalability and security concerns."
- "Run a code review on this diff and synthesize feedback from both reviewers into a prioritized action list."
- "Review the entire /Users/me/project/src directory and identify the top 3 architectural issues."Troubleshooting LAD MCP Server
Reviews fail with 'Invalid API key' from OpenRouter
Ensure OPENROUTER_API_KEY is set correctly in the env block of your MCP config. The key must start with 'sk-or-'. Check your OpenRouter dashboard to confirm the key is active and has remaining credits.
Reviews time out for large codebases
Increase OPENROUTER_REVIEWER_TIMEOUT_SECONDS (default 300). For very large directories, review individual files or subdirectories rather than the entire project at once.
'uvx' command not found
Install uv and uvx with 'pip install uv' or on macOS with 'brew install uv'. Ensure the install location is in your PATH and restart your terminal.
Frequently Asked Questions about LAD MCP Server
What is LAD MCP Server?
LAD MCP Server is a Model Context Protocol (MCP) server that lad mcp server: autonomous code & system design review for ai coding agents (claude code, cursor, codex, etc.). features multi-model consensus via openrouter and context-aware reviews via serena. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LAD MCP Server?
Follow the installation instructions on the LAD MCP Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with LAD MCP Server?
LAD MCP Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LAD MCP Server free to use?
Yes, LAD MCP Server is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
LAD MCP Server Alternatives — Similar Developer Tools Servers
Looking for alternatives to LAD MCP Server? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up LAD MCP Server in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use LAD MCP Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.