Vreme Temporal MCP
Provides AI assistants with rich temporal intelligence including timezone conversions, 9 cultural calendars (Hebrew, Islamic, Chinese, etc.), astronomical events, Islamic prayer times, and context-aware activity appropriateness recommendations.
README
Vreme Temporal MCP
Temporal intelligence for AI assistants
Give your AI assistant rich temporal awareness — timezone intelligence, cultural calendars, astronomical events, and time-sensitive context.
Works with Cursor, VS Code, Claude Desktop, Continue, Cline, and any MCP-compatible client.
What This Does
Instead of just knowing what time it is, your AI gets rich temporal context:
You: "What time is it in Tokyo?"
Claude: "Sunday, November 30, 2025 at 1:36 PM JST. Sunset in 2 hours 51 minutes.
🌅 Sunrise: 6:31 AM
🌇 Sunset: 4:28 PM
🌙 Moon: Full Moon (70% illuminated)
📅 Hebrew: 10 Kislev 5786
📅 Islamic: 9 Jumada al-Thani 1447 AH
📅 Chinese: Year 2025, Month 10, Day 11 (Metal Snake)
⏰ Weekend - Not appropriate for work calls"
Features
- 🌍 200+ Timezones - All pytz timezones with DST handling
- 📅 9 Cultural Calendars - Hebrew, Islamic, Chinese, Hindu, Persian, Buddhist, Bahá'í, Ethiopian, Mayan
- 🕌 Islamic Prayer Times - All 5 daily prayers with qibla direction
- 🌅 Astronomical Events - Sunrise, sunset, moon phases, twilight times
- ✅ Activity Appropriateness - Smart recommendations for calls, meetings, work
- 🍽️ Religious Observances - Fasting detection, work restrictions, holiday awareness
- 💬 Natural Language - No rigid schemas, just ask naturally
Installation
npm install -g @vreme/temporal-mcp
Configuration
Add to your MCP client configuration:
Claude Desktop:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"vreme": {
"command": "vreme-temporal-mcp"
}
}
}
Continue / Cline:
Add to your MCP configuration following their respective setup guides.
Restart your AI client and you're ready!
Example Queries
Time & Timezones
- "What time is it in Tokyo?"
- "Current time in New York"
- "What timezone is Paris in?"
Cultural Intelligence
- "Is it Shabbat in Jerusalem?"
- "Is it Ramadan?"
- "When is Chinese New Year?"
- "What's the Hebrew date today?"
- "When is Diwali 2025?"
Activity Appropriateness
- "Is it a good time to call someone in Tokyo?"
- "Can I email someone in Jerusalem right now?"
- "Should I call Berlin now?"
Astronomical Data
- "What time is sunrise in Tokyo?"
- "When does the sun set in Paris?"
- "What's the moon phase?"
Prayer Times
- "What are prayer times in Dubai?"
- "When is Fajr in Istanbul?"
- "Prayer times in New York"
Time Until
- "How long until sunset?"
- "Time until sunrise in Berlin"
How It Works
The MCP server connects your AI client to the Vreme Time API, which provides:
- Natural language parsing - Understands your questions
- Timezone calculations - Accurate time conversions
- Cultural calendar conversions - 9 calendar systems
- Astronomical computations - Sunrise, sunset, moon data
- Activity analysis - Cultural and temporal appropriateness
All responses include full temporal context, not just clock time.
Architecture
AI Client (Claude Desktop / Continue / Cline)
↓ (MCP Protocol)
@vreme/temporal-mcp
↓ (HTTPS)
api.vreme.ai
↓
Temporal Intelligence Engine
- Stateless - No data stored, pure computation
- Fast - <500ms response time (95th percentile)
- Reliable - Built on battle-tested libraries (pytz, astral, hijri-converter)
Supported Features
Cultural Calendars (9)
- Hebrew (with holiday detection)
- Islamic (with Ramadan, prayer times)
- Chinese (lunisolar, zodiac animals)
- Hindu (festival dates)
- Persian (Nowruz, etc.)
- Buddhist (Vesak, observances)
- Bahá'í (calendar system)
- Ethiopian (unique calendar)
- Mayan (long count)
Prayer Times
- All 5 daily prayers (Fajr, Dhuhr, Asr, Maghrib, Isha)
- Multiple calculation methods (MWL, ISNA, Egypt, Makkah, Karachi, Tehran, Jafari)
- Qibla direction to Mecca
- Next prayer countdown
Religious Observances
- Shabbat detection and times
- Ramadan fasting hours
- Jewish holidays and restrictions
- Work permission status
- Fasting day detection
Troubleshooting
MCP Server Not Appearing
- Verify installation:
which vreme-temporal-mcp - Check your client's config file syntax (valid JSON)
- Completely restart your AI client (quit and reopen)
Connection Issues
- Requires internet access (queries api.vreme.ai)
- Check API status:
curl https://api.vreme.ai/health - Firewall/VPN may be blocking
Query Errors
- Try major city names first
- Use simple queries: "What time is it in London?"
- Some obscure locations may not be recognized
API
This MCP server is powered by the public Vreme Time API.
Endpoint: https://api.vreme.ai/query
You can also use the API directly:
curl -X POST https://api.vreme.ai/query \
-H "Content-Type: application/json" \
-d '{"query": "What time is it in Tokyo?"}'
Links
- Website: www.vreme.ai
- Documentation: www.vreme.ai/docs
- Examples: www.vreme.ai/docs/examples
- GitHub: github.com/vreme-ai/temporal-mcp
- API: api.vreme.ai
License
MIT License - Free and open source forever.
About Vreme
Vreme (Bulgarian: "time") is building temporal intelligence for AI. This time service is the first product — validating the architecture for our upcoming temporal memory service.
Time, understood. Your AI knows what time it is anywhere, respects cultural calendars, and understands contextual appropriateness.
Memory, preserved. Coming Q2 2026: Your AI remembers every conversation, every insight, every step of your learning journey.
Questions? hello@vreme.ai
Built with ❤️ for temporal awareness
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。