Knip Mcp Server

MCP开发工具

提供方 gtrias · 包名 @genar/knip-mcp-server

开发工具 stdio · 本地进程 会话登录 社区 / 第三方 CursorCodexZed
查看接入方式

This MCP server provides AI agents with powerful code cleanup capabilities through knip.dev integration. It's designed to work seamlessly with Cursor AI and other MCP-compatible tools to maintain clean, efficient codebases.

一句话选型结论

按资料字段整理

Knip Mcp Server 属于开发工具类 MCP 服务器,stdio · 本地进程,会话登录,可直接接入 Cursor、Codex、Zed,有可直接执行的安装命令。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stdio · 本地进程 鉴权会话登录 部署方式本地部署
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

dead code cleanup typescript mcp server cursor ai tools code analysis refactoring

支持客户端

适用场景

dead codecleanuptypescript

安装与配置

stdio · 本地进程 会话登录
客户端在本机拉起子进程,数据不出本机
npx @genar/knip-mcp-server

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

    stdio 服务在本地起进程,需要先装好 Cross-platform,再按安装命令拉取依赖。

  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。
  • 已适配 Cursor、Codex、Zed,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好会话登录对应的凭据,并按最小权限配置。
  • 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。
  • 已经在用 Cursor、Codex 的用户,接入路径最短。
  • 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

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 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
Knip Mcp Server当前 未标注 stdio · 本地进程 本地部署 有 未标注
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gtrias上游标注的维护方 gtrias
分类开发工具本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式会话登录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@genar/knip-mcp-server · Cross-platform本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

9.1 KB
来自项目仓库与上游目录的原文,未做删改

@genar/knip-mcp-server

A Model Control Protocol (MCP) server that integrates with knip.dev to help AI agents identify and clean up unused files, imports, exports, and dependencies in JavaScript/TypeScript projects.

Overview

This MCP server provides AI agents with powerful code cleanup capabilities through knip.dev integration. It's designed to work seamlessly with Cursor AI and other MCP-compatible tools to maintain clean, efficient codebases.

Features

  • Code Analysis: Run comprehensive knip analysis to find unused code
  • Unused File Detection: Identify files that are no longer referenced
  • Import/Export Cleanup: Find and remove unused imports and exports
  • Dependency Management: Detect unused npm dependencies and devDependencies
  • Safe Operations: Built-in safety checks and backup mechanisms
  • Workspace Support: Full support for monorepo and workspace setups
  • Dry Run Mode: Preview changes before applying them

Installation```bash

npm install -g @genar/knip-mcp-server


Or in your project:```bash
npm install @genar/knip-mcp-server

Usage

As an MCP Server

Run the server directly:```bash
knip-mcp-server


Or use npx:```bash
npx @genar/knip-mcp-server

Configuration

Configure via environment variables:```bash
export KNIP_PROJECT_ROOT="/path/to/your/project"
export KNIP_CONFIG_PATH="/path/to/knip.json"
export KNIP_BACKUP_DIR="/path/to/backups"
export KNIP_LOG_LEVEL="info"
export KNIP_SAFE_MODE="true"


### Integration with Cursor AI

#### Option 1: MCP Server Configuration

1. In Cursor AI settings, navigate to MCP configuration
2. Add a new MCP server:
   - Name: "Knip Code Cleanup"
   - Command: `npx @genar/knip-mcp-server`
3. Save and restart Cursor AI

#### Option 2: Cursor Rules Configuration

You can also integrate this MCP server through Cursor's rules system by creating a `.cursor/rules` directory in your project root and adding the following configuration:

1. Create the rules directory structure:```bash
mkdir -p .cursor/rules
  1. Create a knip rule file (.cursor/rules/knip-mcp.md):```markdown

Knip Code Cleanup Rules

You have access to the Knip MCP server for code cleanup tasks. Use these tools proactively to maintain clean code:

Available Tools

  • knip_scan - Run comprehensive code analysis
  • knip_get_unused_files - Find unused files
  • knip_get_unused_exports - Find unused exports
  • knip_get_unused_imports - Find unused imports
  • knip_get_unused_dependencies - Find unused dependencies
  • knip_remove_unused_files - Safely remove unused files
  • knip_remove_unused_imports - Clean up unused imports
  • knip_fix_issues - Auto-fix common issues
  • knip_get_config - View knip configuration
  • knip_validate_config - Validate knip config

Usage Guidelines

  1. After implementing features: Always run knip_scan to identify cleanup opportunities
  2. Before commits: Use knip_fix_issues with dryRun: true to preview cleanup
  3. Regular maintenance: Run knip_get_unused_dependencies to audit packages
  4. Safety first: Always use dry-run mode first, create backups for destructive operations

Workflow Integration

When asked to implement features:
1. Complete the implementation
2. Run knip_scan to analyze unused code
3. Use knip_remove_unused_imports to clean imports
4. Check knip_get_unused_files for orphaned files
5. Apply fixes with appropriate safety measures

Safety Measures

  • All destructive operations default to dry-run mode
  • Backups are created automatically before modifications
  • File limits prevent accidental bulk deletions
  • Safe mode protects critical files (package.json, etc.)

Remember: Always review suggestions before applying changes to ensure they don't break functionality.


3. Create a main rules file (`.cursor/rules/main.md`) that includes knip rules:```markdown
# Project Development Rules

Include code cleanup and maintenance guidelines.

@knip-mcp.md

## Code Quality Standards

- Use the Knip MCP server for regular code cleanup
- Maintain clean imports and remove unused dependencies
- Follow the knip workflow after feature implementation
  1. Optional: Add to your .gitignore if you want to keep rules private:```bash
    echo ".cursor/" >> .gitignore

#### Option 3: Per-Project MCP Configuration

Create a local MCP configuration file in your project root (`.mcp-config.json`):```json
{
  "servers": {
    "knip": {
      "command": "npx",
      "args": ["@genar/knip-mcp-server"],
      "env": {
        "KNIP_PROJECT_ROOT": ".",
        "KNIP_LOG_LEVEL": "info",
        "KNIP_SAFE_MODE": "true"
      }
    }
  }
}

Then reference this configuration in Cursor's MCP settings.

Available Tools

knip_scan

Run comprehensive knip analysis on your project.

Parameters:
- projectPath (optional): Project path to analyze
- workspace (optional): Specific workspace for monorepos
- includePaths (optional): Array of paths to include
- excludePaths (optional): Array of paths to exclude
- dryRun (default: true): Run without making changes

knip_get_unused_files

Get a list of unused files in the project.

Parameters:
- workspace (optional): Specific workspace to analyze

knip_get_unused_exports

Get unused exports organized by file.

Parameters:
- workspace (optional): Specific workspace to analyze
- filePath (optional): Get exports for specific file only

knip_get_unused_imports

Get unused imports organized by file.

Parameters:
- workspace (optional): Specific workspace to analyze
- filePath (optional): Get imports for specific file only

knip_get_unused_dependencies

Get unused npm dependencies and devDependencies.

Parameters:
- workspace (optional): Specific workspace to analyze
- type (optional): 'dependencies', 'devDependencies', or 'all'

knip_remove_unused_files

Safely remove unused files with backup options.

Parameters:
- files (optional): Specific files to remove, or all if empty
- dryRun (default: true): Preview mode
- createBackup (default: true): Create backups before removal
- backupDir (optional): Custom backup directory
- maxFiles (default: 50): Safety limit

knip_remove_unused_imports

Remove unused imports from a specific file.

Parameters:
- filePath (required): File to clean up
- imports (optional): Specific imports to remove
- dryRun (default: true): Preview mode
- createBackup (default: true): Create backup before changes

knip_fix_issues

Automatically fix common knip issues.

Parameters:
- issueTypes (default: ['imports']): Types of issues to fix
- dryRun (default: true): Preview mode
- createBackup (default: true): Create backups
- maxFiles (default: 25): Safety limit

knip_get_config

Get the current knip configuration.

Parameters:
- projectPath (optional): Project path
- configPath (optional): Specific config file path

knip_validate_config

Validate knip configuration for correctness.

Parameters:
- projectPath (optional): Project path
- configPath (optional): Specific config file path
- config (optional): Configuration object to validate

Example AI Agent Workflows

1. Code Cleanup After Feature Implementation```

AI Agent: I just implemented a new authentication feature. Let me clean up any unused code.

  1. Run knip_scan to get overview of unused code
  2. Use knip_get_unused_imports to find unused imports
  3. Apply knip_remove_unused_imports to clean up imports
  4. Check knip_get_unused_files for any orphaned files
  5. Safely remove files using knip_remove_unused_files

### 2. Dependency Audit```
AI Agent: Let me audit our dependencies for unused packages.

1. Run knip_get_unused_dependencies
2. Review the list of unused dependencies
3. Generate recommendation report for package.json cleanup

3. Project Health Check```

AI Agent: Let me analyze the overall health of this codebase.

  1. Run knip_scan for comprehensive analysis
  2. Use knip_validate_config to check configuration
  3. Generate health report with recommendations

## Safety Features

- **Dry Run Mode**: All destructive operations default to dry-run mode
- **Backup Creation**: Automatic backups before file modifications
- **Safe Mode**: Prevents removal of critical files (package.json, etc.)
- **File Limits**: Configurable limits on batch operations
- **Error Handling**: Comprehensive error reporting and recovery

## Configuration

The server supports knip configuration files:
- `knip.json`
- `knip.jsonc`
- `.knip.json`
- `.knip.jsonc`
- `knip.config.js`
- `knip.config.ts`

## Development```bash
# Clone the repository
git clone https://github.com/gtrias/knip-mcp-server.git

# Install dependencies
npm install

# Build the project
npm run build

# Run in development mode
npm run dev

# Run tests
npm test

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests
  5. Submit a pull request

License

MIT License - see LICENSE file for details.

Support

  • GitHub Issues: Report bugs or request features
  • Documentation: Full documentation

Related Projects

  • knip.dev - The underlying code analysis tool
  • MCP SDK - Model Context Protocol implementation
  • Cursor AI - AI-powered code editor with MCP support

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Knip Mcp Server 怎么安装?

在客户端按下面的安装命令接入:npx @genar/knip-mcp-server。对应的包名是 @genar/knip-mcp-server。装完在客户端配置里引用同一个包或端点。

Knip Mcp Server 怎么在 Cursor、Codex、Zed 里配置?

它的传输方式是stdio · 本地进程,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,配置才会生效。

Knip Mcp Server 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。

Knip Mcp Server 需要 API Key 吗?

资料标注需要会话登录认证,使用前准备好对应凭据,并按最小权限配置。

Knip Mcp Server 支持哪些客户端?

资料标注支持 Cursor、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Knip Mcp Server 能提供哪些能力?

资料显示能力标签包括 dead code、cleanup、typescript、mcp server、cursor、ai tools。具体工具清单以官方文档为准。

Knip Mcp Server 需要什么运行环境?

运行时为 Cross-platform;属于本地进程,需要在本机装好运行环境。

Knip Mcp Server 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

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 未标注。