prioritization
An MCP server that provides a drag-and-drop UI for prioritizing list items, allowing users to reorder items interactively and send the prioritized list back to the chat. It supports MCP Apps UI rendering and falls back to text instructions for hosts without UI support.
README
MCP Prioritization
A "human prioritization" MCP server built with the official MCP TypeScript SDK
v2 (@modelcontextprotocol/server@^2.0.0) and the MCP Apps extension:
the human_prioritization tool ships an interactive ui:// drag-and-drop
list that hosts like Claude Cowork render as a sandboxed iframe. Reorder the
items, press "Send priorities to chat", and the ranked list comes back
into the conversation as Prioritized: 1. ... 2. ....
Try the deployed server
A live instance runs at https://mcp-prioritization.netlify.app/mcp — add it to Claude as a custom connector (Customize → Connectors → Add → Add custom connector → Remote MCP server URL; details in docs/claude.md).

Example queries to force the MCP tool to be picked up:
List top 10 biggest cities in Lithuania
Let me prioritize cities to visit
Requires at least a Sonnet-tier model — Haiku did not call the tool in testing.
Setup
Requires Node.js 26 (see .nvmrc) and uses TypeScript 7 (native compiler).
nvm use # picks up .nvmrc
npm install
npm run typecheck # tsc --noEmit
Quick test
npx @modelcontextprotocol/inspector --cli npx tsx src/stdio.ts --method tools/list | jq .
Documentation
Full documentation lives in docs/index.md (Open Knowledge Format bundle):
- Architecture — tool,
ui://view, protocol flow, transports - Claude — Claude Code / Desktop / Cowork setup and MCP Apps support matrix
- VS Code — seeing the widget in VS Code's native chat
- ChatGPT — adding the deployed server as a ChatGPT plugin
- Netlify —
/mcpendpoint, first-time project creation, GitHub Actions
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。