Review-Code
# 代码审查工具 Review Code
一个基于Model Context Protocol (MCP)的代码审查工具服务器，提供多维度的代码审查和打分功能。
A code review tool server based on Model Context Protocol (MCP), providing multi-dimensional code review and scoring functions.## 工具列表 Tool List
本MCP服务封装下列工具，可让模型通过标准化接口调用以下功能。 本MCP服务封装下列工具，可让模型通过标准化接口调用以下功能。
| 工具 Tool | 描述 Description |
|-------|--------------------|
| review_code | 构建用于代码整体审查与打分的 LLM 提示词（不直接调用 LLM） |
| review_diff | 构建用于 Git diff 变更审查与打分的 LLM 提示词（不直接调用 LLM） |
| review_file | 构建用于单文件审查与打分的 LLM 提示词（不直接调用 LLM） |
| parse_review_score | 从审查文本中解析评分（提取 '总分:XX分' 格式） |
## 检查服务 ## Inspector
工具在线测试： [https://mcp.xiaobenyang.com/inspector/1777316659306499](https://mcp.xiaobenyang.com/inspector/1777316659306499)
Online Tool test [https://mcp.xiaobenyang.com/inspector/1777316659306499](https://mcp.xiaobenyang.com/inspector/1777316659306499)
## 服务配置 MCP Server Config
> #### 如何获取 XBY-APIKEY ？ How to get XBY-APIKEY ?
> 访问小笨羊科技网站 [https://xiaobenyang.com](https://xiaobenyang.com)，注册用户即可获得APIKEY
> Visit XiaoBenYang website [https://xiaobenyang.com](https://xiaobenyang.com), register and get the APIKEY.
### SSE
```json
{
"mcpServers": {
"代码审查工具": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "sse",
"url": "https://mcp.xiaobenyang.com/1777316659306499/sse"
}
}
}
```
### STREAMABLE HTTP
```json
{
"mcpServers": {
"代码审查工具": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "streamable_http",
"url": "https://mcp.xiaobenyang.com/1777316659306499/mcp"
}
}
}
```
### STDIO
```json
{
"mcpServers": {
"代码审查工具": {
"command": "npx",
"args": [
"-y",
"xiaobenyang-mcp"
],
"env": {
"XBY_APIKEY": "<YOUR_XBY_APIKEY>",
"mcpId": "1777316659306499",
},
"transport": "stdio"
}
}
}
```
TDQS
Scored across 4 tools
The tools have distinct purposes: parse_review_score extracts scores from text, while the other three build prompts for different code review contexts (overall code, Git diff, single file). However, review_code, review_diff, and review_file could be confused as they all build LLM prompts for review, differing only in input scope. Descriptions clarify this, but the overlap in function is notable.
All tool names follow a consistent verb_noun pattern with snake_case: parse_review_score, review_code, review_diff, review_file. The naming is predictable and readable, with no deviations in style or convention across the set.
With 4 tools, the count is well-scoped for a code review server. Each tool serves a clear purpose: one for parsing scores and three for building review prompts across different contexts. This is neither too thin nor too heavy for the domain.
The server covers parsing scores and building prompts for various review types, but there are notable gaps. It lacks tools for executing reviews (e.g., calling an LLM), managing review workflows, or handling feedback beyond scores. This limits agents to only prompt construction and score extraction, missing core review operations.