Ndlovu Code Reviewer (Shaunie2fly)

MCP开发工具

提供方 未标注

开发工具 HTTP · 远程 未标注 社区 / 第三方
查看接入方式

全面解析Ndlovu Code ReviewerMCP Server的核心功能、安装配置和实用案例。作为顶级Model Context Protocol服务器,Ndlovu Code Reviewer能让AI助手访问实时数据、执行操作,为您提供更智能的工作体验和自动化解决方案。

一句话选型结论

按资料字段整理

Ndlovu Code Reviewer (Shaunie2fly) 属于开发工具类 MCP 服务器,HTTP · 远程,鉴权方式未标注,有可直接复制的远程端点配置。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式HTTP · 远程 鉴权未标注 部署方式远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

安装与配置

HTTP · 远程 未标注
连远程 HTTPS 端点,通常为 Streamable HTTP
npm install -g @google/gemini-cli\"

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    确认你的客户端支持远程端点,并拿到服务地址。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Ndlovu Code Reviewer (Shaunie2fly)当前 未标注 HTTP · 远程 远程部署 有 2026-05-17
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类开发工具本站按上游分类展示
连接方式HTTP · 远程连远程 HTTPS 端点,通常为 Streamable HTTP
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · Node.js本地安装时用到的包标识与运行时
部署类型远程部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

7.9 KB
来自项目仓库与上游目录的原文,未做删改

Code Review MCP Server

A Gemini-CLI (for now), powered code review assistant that runs as a Model Context Protocol (MCP) server.

Why this project exists

Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer:

  • Automates the busywork of gathering diffs and lint results from local, uncommitted changes.
  • Streams that context into the Gemini CLI so the model can focus on actionable insights.
  • Returns a structured JSON review that fits naturally into MCP-compatible clients.

What it does

  • Connects to MCP clients over stdio using the official @modelcontextprotocol/sdk.
  • Runs a "hybrid" review workflow that gathers git diff output and linter findings.
  • Falls back between ESLint, JSHint, and TypeScript to maximise coverage across projects.
  • Safely invokes the Gemini CLI, handling long prompts and timeouts.
  • Ships as TypeScript with Zod-backed types for predictable MCP responses.

Requirements

  • Node.js 18 or later (ES modules and AbortSignals are used throughout).
  • npm (installed with Node.js).
  • Git (used to collect local diffs).
  • Google Gemini CLI (gemini) installed and authenticated. See the Gemini quickstart for setup instructions.

Installation```bash

git clone https://github.com/<your-org>/ndlovu-code-reviewer.git
cd ndlovu-code-reviewer
npm install
npm run build


If you plan to iterate on the TypeScript source, you can skip `npm run build` and rely on the dev script described below.

## Usage

### Start the MCP server```bash
npm start

The server communicates over stdio, so it is ready to be registered with any MCP-compatible client (e.g. IDE integrations or assistant sandboxes). Once connected, call the review-local-changes tool to trigger the hybrid analysis and receive the JSON review.

How to call the MCP tool

The server exposes a single tool called review-local-changes that performs comprehensive analysis of your local, uncommitted code changes.

Prerequisites:
- You must have uncommitted changes in your git repository
- Changed files should be JavaScript, TypeScript, or Vue files (.js, .ts, .tsx, .vue)
- The Gemini CLI must be installed and authenticated

Using the tool:

Once your MCP client is connected to the server, you can call the review-local-changes tool. The tool:

  1. Automatically detects changes - Finds all modified/added JS/TS/Vue files using git diff
  2. Runs static analysis - Executes the best available linter (ESLint, JSHint, or TypeScript compiler)
  3. Performs AI review - Sends the combined context to Gemini CLI for intelligent analysis
  4. Returns structured results - Provides a JSON response with findings and recommendations

How to use it with Claude Code:

For best results, be explicit about using the code review functionality. While natural language requests sometimes work, the most reliable approach is to use specific keywords:

Most reliable requests (recommended):
- "Use the code review tool to analyze my changes"
- "Run code review on my local changes"
- "Perform a comprehensive code review of my uncommitted changes"
- "Analyze my code changes with static analysis"

Natural language requests (may work but less reliable):
- "Please review my local changes"
- "Can you analyze the code changes I've made?"

Explicit tool invocation (most reliable):
- "Use the review-local-changes tool"
- "Call the review-local-changes tool to check my modifications"

The tool has been enhanced with better descriptions to help Claude recognize when to use it, but being specific about "code review," "analyze changes," or mentioning the tool name directly will give you the most consistent results.

Example output format:json { &quot;summary&quot;: &quot;Overview of changes made&quot;, &quot;assessment&quot;: &quot;Overall code quality evaluation&quot;, &quot;findings&quot;: [ { &quot;filePath&quot;: &quot;src/example.js&quot;, &quot;lineNumber&quot;: 42, &quot;severity&quot;: &quot;warning&quot;, &quot;category&quot;: &quot;style&quot;, &quot;comment&quot;: &quot;Detailed explanation of the issue&quot;, &quot;suggestion&quot;: &quot;Specific recommendation for improvement&quot; } ] }

Note: If no relevant files have been changed, the tool will return a "No relevant files changed" message, which is normal behavior.

Local development

  • npm run dev – Launches the server with ts-node for rapid iteration.
  • npm run build – Produces the compiled JavaScript output in dist/.

The project structure is intentionally small:

  • src/ – TypeScript source for the MCP server.
  • dist/ – Compiled JavaScript created by npm run build.
  • assets/ – Static assets, including the logo used above.

Connect from MCP clients

Before wiring the server into any client, make sure you have run npm run build so dist/index.js exists. The commands below assume you execute the client from the repository root so the server can read your git workspace.

Claude Code (VS Code extension)

  1. In VS Code, open the command palette (Cmd/Ctrl+Shift+P) and run Claude: Edit Config File.
  2. Locate the mcpServers section (create it if needed) and add an entry similar to:json { &quot;mcpServers&quot;: { &quot;ndlovu-code-reviewer&quot;: { &quot;command&quot;: &quot;node&quot;, &quot;args&quot;: [&quot;/absolute/path/to/ndlovu-code-reviewer/dist/index.js&quot;], &quot;cwd&quot;: &quot;/absolute/path/to/ndlovu-code-reviewer&quot; } } }

  3. Save the file and run Claude: Restart Claude Code (or reload VS Code) so the server appears under Tools.

  4. Enable the tool for a conversation; Claude Code will stream review-local-changes results directly in the sidebar.

Gemini CLI

  1. From the project root run:bash gemini mcp add ndlovu-code-reviewer node $(pwd)/dist/index.js

  2. Verify the registration with gemini mcp list.

  3. Launch gemini from the same repository directory and use the review-local-changes tool (e.g., run :tools in the CLI and select it). The CLI spawns the server and forwards stdout back as the review JSON.

Roo Code

  1. Open Roo Code and click the server icon in the top of the Roo panel.
  2. Choose Add MCP Server → STDIO and fill in:
    - Name: ndlovu-code-reviewer
    - Command: node
    - Arguments: /absolute/path/to/ndlovu-code-reviewer/dist/index.js
    - Working Directory: /absolute/path/to/ndlovu-code-reviewer
  3. Save the configuration and enable the server for your workspace. Roo stores it in either the global mcp_settings.json or the project .roo/mcp.json file.
  4. To share with teammates, commit a .roo/mcp.json that contains your preferred launch command, for example:json { &quot;mcpServers&quot;: { &quot;ndlovu-code-reviewer&quot;: { &quot;command&quot;: &quot;npm&quot;, &quot;args&quot;: [&quot;run&quot;, &quot;start&quot;], &quot;cwd&quot;: &quot;.&quot; } } }

Roo resolves the working directory relative to the project root, so the npm run start script builds on the repository’s own package scripts.

Codex CLI

  1. Register the server once:bash codex mcp add ndlovu-code-reviewer node $(pwd)/dist/index.js

  2. Use codex mcp list to confirm the entry, then start Codex from the repository root. The CLI exposes review-local-changes as a tool you can call inside interactive runs.

Contributing

Contributions are very welcome. If you have ideas for new tools, better linters, or improved prompts:

  1. Open an issue or discussion so we can align on scope.
  2. Fork the repository and create a feature branch.
  3. Add or update documentation/tests where it helps future contributors.
  4. Submit a pull request describing the change and how you validated it.

If you're unsure where to start, feel free to reach out—there is plenty of room to expand the reviewer’s capabilities, add client examples, and tighten the prompts.

License

This project is licensed under the ISC License. See LICENSE (if present) for details.

常见问题

7 问
答案由本站依据条目字段整理,不引用上游原文
Ndlovu Code Reviewer (Shaunie2fly) 怎么安装?

在客户端按下面的安装命令接入:npm install -g @google/gemini-cli\"。装完在客户端配置里引用同一个包或端点。

Ndlovu Code Reviewer (Shaunie2fly) 怎么在客户端里配置?

它的传输方式未标注,在客户端 MCP 配置里按官方文档填写启动命令和参数,保存后重启客户端生效。

Ndlovu Code Reviewer (Shaunie2fly) 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Ndlovu Code Reviewer (Shaunie2fly) 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Ndlovu Code Reviewer (Shaunie2fly) 能提供哪些能力?

资料显示能力标签包括 代码审查、静态分析、JavaScript、Git集成、HTTP。具体工具清单以官方文档为准。

Ndlovu Code Reviewer (Shaunie2fly) 需要什么运行环境?

运行时为 Node.js;属于远程端点,不需要在本地装运行时。

Ndlovu Code Reviewer (Shaunie2fly) 是本地还是远程?

它是远程端点,连服务地址即可。传输方式为HTTP · 远程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。