Obsidian Diary MCP Server
Enables AI-powered journaling in Obsidian with dynamic reflection prompts generated from recent entries and automatic backlinks between related diary entries. Supports adaptive templates that learn from writing patterns and smart content similarity linking.
README
Obsidian Diary MCP Server
Establish a daily journaling habit that'll unlock superpowers in your career and life. AI analyzes your entries to generate personalized prompts while keeping everything local.
What it enables: Daily reflection • Smart prompts • Complete privacy
What You Need
Software:
- uv (Python installer)
- Ollama (runs AI locally, ~5GB)
- A CLI that works with MCP
For Obsidian:
- A dedicated Obsidian vault that only contains diary entries
- Read/write access to that vault
Quick Start
1. Clone the repo:
git clone https://github.com/madebygps/obsidian-diary-mcp.git
2. Enter directory:
cd obsidian-diary-mcp
3. Install dependencies:
uv sync
4. Make script executable:
chmod +x start-server.sh
5. Install GitHub Copilot CLI:
npm install -g @github/copilot
6. Launch Copilot:
copilot
7. Add MCP server:
/mcp add
Provide these values:
- Name:
diary, - Command:
/full/path/to/obsidian-diary-mcp/start-server.sh, - Environment:
DIARY_PATH=/path/to/your/diary-vault
How to Use
Best way: Use Copilot CLI interactively
- Start Copilot CLI:
copilot - In the interactive session, use natural prompts:
- "create a diary entry for today"
- "show me my recent entries"
- "complete today's entry with backlinks"
- "read my entry from October 3rd"
Alternative: Command line usage
copilot "use create_diary_entry_file"- Make new entrycopilot "use list_recent_entries"- See recent entriescopilot "use complete_diary_entry"- Add backlinks when donecopilot "use read_diary_entry for 2024-10-03"- Read specific entry
If It Breaks
Server problems:
- Check config:
cat ~/.copilot/mcp-config.json - Make script runnable:
chmod +x start-server.sh - Test it:
./start-server.sh - Restart your CLI
Other problems:
- Check diary folder exists:
ls -la $DIARY_PATH - Check uv works:
uv --version - Check Ollama runs:
curl http://localhost:11434/api/tags - Test AI:
ollama run llama3.1 "test"
Command problems:
- Be specific:
copilot "use create_diary_entry_file tool" - Check what's available:
copilot "what MCP tools are available?" - Use YYYY-MM-DD for dates
How It Works
- Prompts: Reads your old entries and makes new questions
- Links: Connects entries by date
[[2024-10-03]]and topic#work-stress - Fast: Caches stuff so it doesn't ask AI the same thing twice
- Adaptive: No hardcoded content, learns from your writing
- Obsidian: Works with backlinks, tags, and graph view
Entry Format
Files are stored as YYYY-MM-DD.md in your diary vault:
# Thursday, October 3, 2024
## Reflection Prompts
**How did work play out today?**
**What patterns am I noticing in my thinking?**
**What challenged me most today and why?**
## Brain Dump
Your thoughts and experiences...
---
## Memory Links
**Temporal:** [[2024-09-28]] • [[2024-09-30]]
**Topics:** #work-stress #personal-growth #decision-making
License: MIT • Requirements: Python 3.8+, FastMCP
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。