ShortcutSistem + Band MCP Server

ShortcutSistem + Band MCP Server

Combines Band AI platform control with ShortcutSistem digital marketing tools for SEO, social media, and content creation.

Category
访问服务器

README

ShortcutSistem + Band MCP Server

Combined MCP server for Cursor Cloud — gives you Band platform control + ShortcutSistem tools in one HTTP connection.

Cursor Cloud ──MCP (HTTP)──→ This Server ──REST──→ Band AI
                                            └──→ ShortcutSistem Tools (built-in)

Requirements

  • Python 3.11+ (band-sdk requires 3.11)
  • Band API key from https://app.band.ai/settings/api-keys

Tools Available

Band Platform Tools (5)

Tool Description
band_list_agents List all your Band agents
band_list_my_chats See recent Band conversations
band_send_message Send a message to any agent
band_get_chat_history Read conversation history
band_trigger_agent Trigger a specific agent to run a task

ShortcutSistem Tools (7)

Tool Description
run_omni_audit(url) Full digital audit — SEO, AI visibility (GEO), performance, security
check_homepage_seo(url) Quick SEO check with scorecard
check_website_health(url) Uptime, SSL, response time, security headers
write_tiktok_captions(topic, count) Indonesian TikTok captions for UMKM
write_instagram_captions(topic, count) Indonesian IG captions for UMKM
get_ss_video_prompt(industry, brand) ShortcutSistem fashion video prompts for MiniMax + BytePlus
create_content_calendar(topic, weeks) 4-week content calendar for Indonesian social media

Setup

1. Get Your Band API Key

https://app.band.ai/settings/api-keys

2. Deploy to Railway (Recommended)

  1. Push to GitHub:

    cd shortcutsistem-band-mcp
    git init && git add . && git commit -m "Initial commit"
    # Create repo on GitHub: https://github.com/new
    git remote add origin https://github.com/Therealratoshen/shortcutsistem-band-mcp.git
    git push -u origin main
    
  2. Deploy on Railway:

    • Go to railway.app → New Project → Deploy from GitHub
    • Connect the shortcutsistem-band-mcp repo
    • Add environment variable: BAND_API_KEY = band_a_1781922604_x9vo02skdxefhp8JqL3jzesZKGDb5v1b
    • Railway auto-detects Python from pyproject.toml
    • Wait 2-3 minutes → copy the URL (e.g. https://shortcutsistem-band-mcp.up.railway.app)
  3. Test the endpoint:

    https://shortcutsistem-band-mcp.up.railway.app/mcp/
    

    You should see an MCP welcome message.

3. Connect to Cursor Cloud

Add to Cursor Cloud MCP settings (~/.cursor/mcp_settings.json):

{
  "mcpServers": {
    "shortcutsistem-band": {
      "url": "https://shortcutsistem-band-mcp.up.railway.app/mcp/"
    }
  }
}

Restart Cursor. The tools will appear in the agent panel.

4. Local Development

cd shortcutsistem-band-mcp
cp .env.example .env
# Edit .env and add your BAND_API_KEY
uv sync
uv run python server.py
# Server runs on http://localhost:8000/mcp/

Transport

Uses streamable-http (FastMCP) — compatible with Cursor Cloud MCP HTTP transport.

Not stdio. Not SSE. HTTP with POST + streaming responses.

Troubleshooting

"Module not found: band"

  • Make sure band-client-rest is installed: uv sync or pip install band-client-rest band-sdk

"BAND_API_KEY environment variable is required"

  • Set the BAND_API_KEY environment variable in Railway dashboard

Server starts but tools don't appear in Cursor

  • Check Cursor Cloud MCP settings use /mcp/ suffix on the URL
  • Verify the URL is accessible from the internet (Cursor Cloud runs in browser)

Python version error

  • Ensure Railway uses Python 3.11+ (check in Railway dashboard → Runtime)

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选