@tscafejr/mcp
A collection of MCP servers distributed as a single npm package, including mcp-visualizer which uses Puppeteer for screenshots, typing, and network/console diagnostics on any web framework.
README
@tscafejr/mcp
MCP servers I use across projects distributed as a single npm package with one bin per server.
Installation (consumers)
Wire a server into any MCP client config:
{
"mcpServers": {
"visualizer": {
"command": "npx",
"args": ["-y", "@tscafejr/mcp", "mcp-visualizer"]
}
}
}
Available servers
| Bin | Source | Description |
|---|---|---|
mcp-visualizer |
src/servers/visualizer.ts |
Puppeteer-driven screenshots, typing, and network/console diagnostics. Framework-agnostic — works with Vite, Next.js, CRA, Netlify dev, deploy previews, etc. |
mcp-visualizer configuration
Target URL is resolved in this order (highest to lowest):
- Per-call
base_urlarg — full URL, e.g.https://my-site.netlify.apporhttp://localhost:8888. - Per-call
portarg — localhost shorthand. MCP_DEV_SERVER_URLenv — full base URL.MCP_DEV_SERVER_HOST+MCP_DEV_SERVER_PORTenv.- Default:
http://localhost:3000.
Example MCP client configs:
// Vite project
{ "mcpServers": { "visualizer": {
"command": "npx", "args": ["-y", "@tscafejr/mcp", "mcp-visualizer"],
"env": { "MCP_DEV_SERVER_PORT": "5173" }
}}}
// Netlify dev
{ "mcpServers": { "visualizer": {
"command": "npx", "args": ["-y", "@tscafejr/mcp", "mcp-visualizer"],
"env": { "MCP_DEV_SERVER_PORT": "8888" }
}}}
// Remote deploy preview
{ "mcpServers": { "visualizer": {
"command": "npx", "args": ["-y", "@tscafejr/mcp", "mcp-visualizer"],
"env": { "MCP_DEV_SERVER_URL": "https://preview-123.example.com" }
}}}
Adding a new server
-
Create
src/servers/<name>.ts. Start with a shebang so the built file is directly executable:#!/usr/bin/env node import { Server } from "@modelcontextprotocol/sdk/server/index.js"; import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"; // ... -
Add one line to the
binmap inpackage.json:"bin": { "mcp-visualizer": "dist/servers/visualizer.js", "mcp-<name>": "dist/servers/<name>.js" } -
Build and run locally:
npm run build npm run dev <name> # tsx, no build step npm run start <name> # runs the built dist/ output
That's it — chmod-bins.js reads package.json on every build and marks all bin outputs executable, so new entries pick up automatically.
Add the new row to the table above so consumers know what's available.
Releasing
The release script prompts for the bump type (major / minor / patch), runs npm version, builds, publishes, and pushes the commit + tag to your git remote.
npm run release
Equivalent manual steps if you'd rather drive it yourself:
npm version patch # or: minor / major — bumps, commits, tags
npm publish # prepublishOnly rebuilds dist/
git push --follow-tags # if/when this dir has a git remote
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。