Obsidian Diary MCP

An AI - based local diary MCP service that supports automatic reverse linking, smart tag extraction, and to - do item management. All data is processed locally to ensure privacy and security.

Note-taking tools Knowledge management and memory #Intelligent diary #Local AI #Automatic linking #Privacy and security .Python

rating : 2 points

downloads : 4.9K

update time : 2025-10-09

Open Site

What is Obsidian Diary MCP Server?

This is an intelligent diary assistant that uses local AI technology to automatically analyze your diary content, generate personalized reflection prompts, extract to-do items, create smart tags, and establish automatic links. All processing is done locally to ensure the security of your privacy.

How to use Obsidian Diary?

Simply interact with the AI assistant using simple natural language commands, such as 'Create a memory log for today' or 'Extract today's to-do items'. The system will automatically process your diary content and generate corresponding structured outputs.

Applicable scenarios

Suitable for users who want to establish a systematic diary - keeping habit, individuals who need to organize daily thoughts and tasks, people who like to conduct self - reflection through writing, and Obsidian users who want to enhance their note - taking experience with AI technology.

Main features

AI reflection prompt generation

Based on the diary content of the past 3 days, automatically generate personalized reflection questions to help you think deeply.

Automatic date linking

Automatically create links in the date format [[YYYY - MM - DD]] to facilitate jumping to the diary of a specific date in Obsidian.

Free - writing analysis

Focus on analyzing your free - writing content (rather than prompt responses) to extract real thoughts and themes.

Smart tag extraction

Automatically generate relevant tags based on theme similarity, such as #CareerDevelopment #SelfReflection, etc.

To - do item extraction

Identify action items from free - writing and organize them into a structured to - do list.

Memory trace analysis

Analyze the evolution process of themes and display the changing trends of thoughts and interests.

Sunday comprehensive reflection

Generate 5 comprehensive reflection prompts every Sunday to help with weekly summaries.

Advantages

Completely local processing: All AI analysis runs locally, and data never leaves your device.

Privacy and security: No internet connection is required, protecting the privacy of personal diary content.

Intelligent connection: Automatically discover theme associations between diary entries.

Easy to use: Natural language interaction, no complex technical knowledge is required.

Deep integration with Obsidian: Make full use of Obsidian's linking and chart functions.

Limitations

Requires a local AI environment: Ollama and the corresponding models must be installed and configured.

Technical requirements: Some technical foundation is needed to set up the environment.

Content requirements: At least 50 characters of free - writing content are required for effective analysis.

Link threshold: At least 2 entries with more than 8% theme overlap are required to create a link.

How to use

Environment preparation

Install necessary software: uv package manager, Ollama local AI, MCP client (such as GitHub Copilot CLI), and Obsidian note - taking software.

Download and installation

Clone the project code repository and install dependency packages.

Configure the environment

Copy the environment configuration file and set the storage paths for the diary and planner.

Add to the MCP client

Add the diary server to the MCP client configuration.

Start using

Start the service and interact with the diary assistant using natural language commands.

Usage examples

Daily diary recording

Start writing your daily diary with personalized prompts generated by AI to help you deeply reflect on the day's experiences and feelings.

Task management integration

Automatically extract to - do items from free - writing, avoiding the trouble of manually organizing action items.

Theme discovery and connection

Discover recurring themes in the diary and automatically create relevant tags and links.

Periodic review

Conduct weekly or monthly trend analysis to understand the evolution process of thoughts and interests.

Frequently Asked Questions

Why are no links created between my diary entries?

How to check if the server is running normally?

What should I do if the AI processing speed is very slow?

What special functions are there on Sundays?

How to ensure the privacy and security of my diary content?

Which AI models are supported?

Related resources

Project code repository

Complete source code and latest updates

Ollama official website

Download and documentation for the local AI running environment

Obsidian note - taking software

Official website of the knowledge management and note - taking software

MCP protocol documentation

Official documentation of the Model Context Protocol

uv package manager

A fast Python package management tool

🚀 Obsidian Diary MCP Server

Obsidian Diary MCP Server is an AI - powered journaling solution that performs local processing, creates automatic backlinks, and provides smart prompts, enhancing the journaling experience.

✨ Features

Generate AI - based reflection prompts considering the past 3 calendar days.
Automatically generate day citations with [[YYYY - MM - DD]] backlinks.
Prioritize brain dumps by analyzing the writing content (not prompts).
Extract smart #tag using theme similarity.
Extract to - do items from entries and organize them into checklists.
Analyze memory traces with theme evolution.
Provide Sunday synthesis (weekly reflection prompts).

📦 Installation

Requirements

uv (Python package manager)
Ollama (llama3.1 or compatible model)
MCP client (e.g., GitHub Copilot CLI)
Obsidian vault (for markdown files)

Setup Steps

1. Clone and install:

git clone https://github.com/madebygps/obsidian-diary-mcp.git

cd obsidian-diary-mcp

uv sync

chmod +x start-server.sh

2. Configure:

cp .env.example .env

Edit .env: set DIARY_PATH and PLANNER_PATH (required)

3. Add to MCP client config (e.g., GitHub Copilot CLI):

Name: diary
Command: /full/path/to/obsidian-diary-mcp/start-server.sh

Configuration Details

Configuration (.env):

Required: DIARY_PATH, PLANNER_PATH

Optional: OLLAMA_MODEL (default: llama3.1:latest), OLLAMA_TIMEOUT (60s), OLLAMA_TEMPERATURE (0.7), OLLAMA_NUM_PREDICT (1000 tokens)

💻 Usage Examples

Basic Usage

Create: Use the command "create a memory log for today" to get AI prompts based on the past 3 days.
Write: Open the entry in Obsidian and write freely in the Brain Dump section.
Extract: Run "extract todos from today's entry" to transfer action items to the planner.
Link: Execute "link today's memory log" to auto - generate [[YYYY - MM - DD]] and #tags.
Explore: Utilize Obsidian's backlinks panel and graph view.

Advanced Usage

You can also use more commands like "show themes from last week", "create memory trace for 30 days", "refresh memory links for 30 days".

🔧 Technical Details

How It Works

Local AI: Ollama processes entries locally, ensuring that your content never leaves your machine.
Calendar - Based: It analyzes the past 3 calendar days, not just the last 3 entries.
Brain Dump Focus: It prioritizes your writing over answered prompts when determining themes.
Day Citations: AI cites [Day 1]/[Day 2] and converts them to [[2025 - 10 - 07]] backlinks.
Smart Linking: It uses Jaccard similarity to connect entries with over 8% theme overlap.
Sundays: It provides 5 weekly synthesis prompts (compared to 3 daily prompts).
Todo Extraction: AI identifies action items from brain dumps.

Entry Format

Each entry (YYYY - MM - DD.md) has the following plain - text headers:

## Reflection Prompts
**1. Question with [[2025-10-06]] backlink (reason)...**

---

## Brain Dump
Your thoughts, experiences, observations...

---

## Memory Links
**Temporal connections:** [[2025-10-05]] • [[2025-10-04]]
**Topic tags:** #career-growth #self-reflection

📚 Documentation

Debugging

Logs are stored in the logs/ directory: server - YYYY - MM - DD.log (protocol), debug - YYYY - MM - DD.log (operations).

tail -f logs/debug-$(date +%Y-%m-%d).log  # Watch in real-time
grep ERROR logs/debug-*.log                # Find errors
grep "similarity" logs/debug-*.log         # Debug backlinks

Troubleshooting

Server issues: Check if .env exists and DIARY_PATH and PLANNER_PATH are set. Run ./start - server.sh directly to test.
Ollama issues: Verify if Ollama is running with curl http://localhost:11434/api/tags. Pull the model using ollama pull llama3.1:latest.
No backlinks: You need 2 or more entries with similar themes (over 8% overlap). Ensure the Brain Dump section has substantial content (over 50 chars). Check: grep "Brain Dump" logs/debug-*.log.
Timeouts: Increase OLLAMA_TIMEOUT (90+) and OLLAMA_NUM_PREDICT (2000+) for reasoning models.

📄 License

This project is under the MIT license. It requires Python 3.13+ and FastMCP 2.12.4+ and Ollama.

create_diary_template

Preview the memory log template - Create a complex diary template with in - depth cognitive exploration prompts

Parameters

date : str*

Description

Required: Current date, formatted as YYYY - MM - DD. For 'today', pass the current system date like '2025 - 10 - 07'.

Parameters

focus : str | None*

Description

Optional focus area (e.g., 'Current dilemma', 'Cognitive pattern').

create_diary_entry_file

Create a new memory log - Create a new diary entry for a specific date with AI - generated analysis prompts

Parameters

date : str*

Description

Required: Current date, formatted as YYYY - MM - DD. For 'today', pass the current system date like '2025 - 10 - 07'.

Parameters

focus : str | None*

Description

Optional focus area (e.g., 'Current dilemma', 'Cognitive pattern').

complete_diary_entry

Complete and link the memory log - Automatically generate Obsidian - compatible memory links and provide cognitive analysis

Parameters

date : str*

Description

Required: Current date, formatted as YYYY - MM - DD. For 'today', pass the current system date like '2025 - 10 - 07'.

update_entry_backlinks

Refresh memory links - Update reverse links of existing diary entries based on current content

Parameters

date : str*

Description

Date of the entry, formatted as YYYY - MM - DD.

refresh_recent_backlinks

Batch refresh the memory network - Only update reverse links of recent diary entries, faster than a full refresh

Parameters

days : int*

Description

Number of recent days to update (1 - 365).

read_diary_entry

Read a memory log - Read a specific diary entry by date

Parameters

date : str*

Description

Date of the entry, formatted as YYYY - MM - DD.

list_recent_entries

List recent memory logs - List your recent diary entries

Parameters

count : int*

Description

Number of recent entries to list (1 - 100).

show_themes

Show recurring themes - Show recurring themes and topics from recent memory logs without exposing diary content

Parameters

days : int*

Description

Number of recent days to analyze (1 - 365).

generate_memory_trace_analysis

Generate a memory trace analysis - Analyze existing diary entries to generate a comprehensive analysis report containing themes, patterns, and cognitive insights

Parameters

days : int*

Description

Number of days to analyze (e.g., 30 for last month, 365 for last year).

Parameters

save_to_file : bool*

Description

Whether to save the memory trace to a file in the diary directory.

extract_todos

Extract to - do items from an entry - Extract action items and to - do items from a diary entry and save them to the plan file

Parameters

date : str*