by KevinRabun · MCP 服务器 · ★ 5
Judges Panel An MCP (Model Context Protocol) server that provides a panel of 45 specialized judges to evaluate AI-generated code — acting as an independent quality gate regardless of which project is being reviewed. Combines deterministic pattern matching & AST analysis (instant, offline, zero LLM calls) with LLM-powered deep-review prompts that let your AI assistant perform expert-persona analysis across all 45 domains. Highlights: Includes an App Builder Workflow (3-step) demo for release decisions, plain-language risk summaries, and prioritized fixes — see Try the Demo.
| Stars | 5 |
| Forks | 3 |
| Language | TypeScript |
| Category | MCP 服务器 |
| License | MIT |
| Quality Score | 31.9/100 |
| Open Issues | 3 |
| Last Updated | 2026-04-07 |
| Created | 2026-02-19 |
| Platforms | mcp, node |
| Est. Tokens | ~1811k |
These tools work well together with judges for enhanced workflows:
Explore other popular mcp 服务器 tools:
judges is MCP server with specialized judges to evaluate AI-generated code for security, cost, scalability, cloud readiness, and best practices.. It is categorized as a MCP 服务器 with 5 GitHub stars.
judges is primarily written in TypeScript. It covers topics such as ai-agent, ai-code-review, ai-generated-code.
You can find installation instructions and usage details in the judges GitHub repository at github.com/KevinRabun/judges. The project has 5 stars and 3 forks, indicating an active community.
judges is released under the MIT license, making it free to use and modify according to the license terms.