
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.