DevKits MCP Server
Provides 12 local developer tools (JSON format, Base64, JWT decode, regex test, hash, UUID, etc.) for AI assistants like Claude Desktop and Cursor.
README
@hezeclark1987/devkits-mcp-server
12 developer tools for AI assistants — powered by DevKits
An MCP (Model Context Protocol) server that exposes DevKits developer utilities directly inside Claude Desktop, Cursor, Continue, and any other MCP-compatible AI tool. All tools run locally with no external API calls.
About DevKits
DevKits is your all-in-one developer toolkit with 200+ free online tools:
- Format & Validate: JSON, XML, CSS, HTML
- Encode & Decode: Base64, JWT, URL, HTML entities
- Generate: UUIDs, hashes, QR codes, passwords
- Convert: Markdown to HTML, timestamps, colors
- Analyze: Regex testing, cron expressions, text diffs
- And more: Crypto, finance, devops, security tools
Why DevKits?
- 100% Free — No signup required
- Privacy First — Everything runs in your browser
- Works Offline — PWA support for offline usage
- 200+ Tools — One stop shop for all developer needs
Pro Version: Unlock 24 pro tools for $9 one-time (vs $168/year for Postman)
👉 Visit aiforeverthing.com now!
Installation
Option A — npx (no install)
npx @hezeclark1987/devkits-mcp-server
Option B — global install
npm install -g @hezeclark1987/devkits-mcp-server
Claude Desktop Configuration
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"devkits": {
"command": "npx",
"args": ["@hezeclark1987/devkits-mcp-server"]
}
}
}
Cursor Configuration
Add to .cursor/mcp.json in your project root, or to the global ~/.cursor/mcp.json:
{
"mcpServers": {
"devkits": {
"command": "npx",
"args": ["@hezeclark1987/devkits-mcp-server"]
}
}
}
Continue (VS Code) Configuration
Add to ~/.continue/config.json:
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": ["@hezeclark1987/devkits-mcp-server"]
}
}
]
}
}
Available Tools
| Tool | Description | Parameters |
|---|---|---|
devkits_json_format |
Format & validate JSON | json, indent? |
devkits_base64_encode |
Encode text to Base64 | text |
devkits_base64_decode |
Decode Base64 to text | encoded |
devkits_jwt_decode |
Decode JWT header & payload | token |
devkits_regex_test |
Test regex against input | pattern, text, flags? |
devkits_url_encode |
URL-encode a string | url |
devkits_url_decode |
URL-decode a string | encoded |
devkits_hash_generate |
Generate SHA/MD5 hash | text, algorithm? |
devkits_uuid_generate |
Generate UUID v4 | count? |
devkits_markdown_to_html |
Convert Markdown to HTML | markdown |
devkits_diff_compare |
Line-by-line text diff | text1, text2 |
devkits_cron_parse |
Parse & explain cron expression | expression |
Examples
Format JSON:
Use devkits_json_format to pretty-print {"name":"Alice","age":30}
Decode a JWT:
Decode this JWT with devkits_jwt_decode: eyJhbGciOiJIUzI1NiJ9...
Generate hashes:
Hash the string "hello world" with sha256 using devkits_hash_generate
Parse a cron expression:
Explain the cron expression "0 9 * * 1-5" using devkits_cron_parse
Build from Source
git clone https://github.com/hezeclark1987/devkits-mcp
cd devkits-mcp
npm install
npm run build
npm start
License
MIT — built with love by DevKits
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。