Enhanced Obsidian MCP Server
Enables seamless integration between AI models and Obsidian knowledge bases with 25 advanced tools for note management, intelligent search, AI-powered content analysis, auto-linking, tag management, template systems, and knowledge graph generation.
README
Enhanced Obsidian MCP Server - 25 Advanced AI Tools
π Overview
The Enhanced Obsidian MCP Server is a powerful Model Context Protocol (MCP) server designed for seamless integration between AI models and Obsidian knowledge bases. Provides 25 powerful tools for intelligent knowledge management, automated content analysis, and smart linking capabilities.
β¨ Core Features
- π Seamless Obsidian Integration: Direct access to Obsidian knowledge base through MCP protocol
- π Complete Note Management: Read, create, update, and delete notes with advanced text replacement features
- π Folder Operations: Create, rename, move, and delete folders with full hierarchy support
- π Intelligent Search: Full-text search across all file types with smart scoring
- π€ AI Analysis: Revolutionary strategic insights using TF-IDF framework
- π Auto Backlink Generation: Revolutionary intelligent detection of note names and conversion to wikilinks
- β‘ Precise Editing: Advanced PATCH operations with heading and block-level positioning
- π Dual API Strategy: Obsidian REST API combined with file system fallback for maximum reliability
- π― Context Optimization: Intelligent content summarization for LLM context length management
- π Batch Processing: Efficient bulk operations with progress tracking
β¨ New Features
- π§ 15 New AI-Enhanced Tools for intelligent content analysis
- π Smart Auto-Linking with advanced pattern recognition
- π Knowledge Graph Generation for visualizing note relationships
- π·οΈ Advanced Tag Management with intelligent suggestions
- π Template System for consistent note creation
- π Content Similarity Analysis using TF-IDF and cosine similarity
- π Relationship Analysis for discovering hidden connections
π οΈ Complete Tool Suite (25 Tools)
π Core Note Management (10 Tools)
π Note Operations
| Tool | Description | Detailed Functionality |
|---|---|---|
list_notes |
List all notes in vault with optional folder filtering | Browse vault contents, filter by specific folders, get note metadata (size, dates, paths) |
read_note |
Read individual note content | Retrieve complete note content with metadata, file statistics, and modification history |
read_multiple_notes |
Batch read multiple notes simultaneously | Efficiently load multiple notes at once, perfect for content analysis or bulk operations |
create_note |
Create new notes with content | Generate new markdown files with specified content, automatic directory creation |
update_note |
Advanced content editing with precise positioning | Edit notes with surgical precision - replace text, insert at specific positions, delete sections |
delete_note |
Remove notes from vault | Safely delete notes with confirmation, maintains vault integrity |
move_note |
Rename or relocate notes | Move notes between folders, rename files, automatic link updates |
π Folder & Organization
| Tool | Description | Detailed Functionality |
|---|---|---|
manage_folder |
Full folder operations (create/rename/move/delete) | Complete folder management - create nested structures, reorganize vault hierarchy |
search_vault |
Full-text search across all content | Powerful search with regex support, context snippets, relevance scoring |
auto_backlink_vault |
Intelligent auto-linking with pattern recognition | Scan entire vault, detect note names in content, convert to [[wikilinks]] automatically |
π·οΈ Tag Management System (3 Tools)
| Tool | Description | Detailed Functionality |
|---|---|---|
add_tags |
Add multiple tags to notes | Insert hashtags into note frontmatter or content, support for nested tags (e.g., #project/web) |
list_tags |
List all tags with usage statistics | Comprehensive tag inventory with usage counts, sorting options, tag hierarchy analysis |
search_by_tags |
Advanced tag-based search with AND/OR operators | Complex tag queries - find notes with specific tag combinations, Boolean logic support |
π Template System (4 Tools)
| Tool | Description | Detailed Functionality |
|---|---|---|
create_template |
Create reusable note templates with variables | Design dynamic templates with {{variables}}, support for dates, titles, custom placeholders |
list_templates |
Browse available templates | View all saved templates with metadata, usage statistics, and variable information |
apply_template |
Apply templates with variable substitution | Generate new notes from templates, automatic variable replacement, custom value injection |
delete_template |
Remove unused templates | Clean up template library, maintain template organization |
π§ AI Content Analysis (4 Tools)
| Tool | Description | Detailed Functionality |
|---|---|---|
extract_keywords |
Extract key terms using TF-IDF algorithm | Identify important keywords and phrases, statistical relevance scoring, configurable result count |
generate_summary |
Create intelligent content summaries | Automatic text summarization, extractive summary generation, customizable length |
suggest_tags |
AI-powered tag recommendations | Analyze content and suggest relevant tags, learn from existing tagging patterns |
find_similar_notes |
Discover similar content using cosine similarity | Content-based similarity matching, semantic analysis, threshold-based filtering |
π Knowledge Graph & Analytics (4 Tools)
| Tool | Description | Detailed Functionality |
|---|---|---|
analyze_note_relationships |
Comprehensive relationship mapping | Map connections between notes, analyze link patterns, identify knowledge clusters |
generate_knowledge_graph |
Export graph data for visualization tools | Generate network data in JSON/Cytoscape formats, node/edge definitions, ready for D3.js/Gephi |
find_orphan_notes |
Identify isolated content | Detect notes without links, find disconnected content, vault completeness analysis |
suggest_connections |
AI-powered connection recommendations | Recommend potential links based on content similarity, discover hidden relationships |
π Quick Start
Option 1: NPM Installation (Recommended)
Install globally:
npm install -g @jianruidutong/obsidian-mcp
Or use npx (no installation required):
npx @jianruidutong/obsidian-mcp
Option 2: From Source
Clone and build:
git clone https://github.com/jianruidutong/obsidian-mcp.git
cd obsidian-mcp
npm install
npm run build
npm start
Option 3: Docker Installation
Quick start with Docker:
git clone https://github.com/jianruidutong/obsidian-mcp.git
cd obsidian-mcp
cp .env.example .env
# Edit .env with your vault settings
docker-compose up -d
π For detailed installation instructions, see Installation Guide
βοΈ Configuration
MCP Client Configuration
Option 1: NPM Installation Configuration
{
"mcpServers": {
"obsidian-mcp": {
"command": "npx",
"args": ["-y", "@jianruidutong/obsidian-mcp"],
"env": {
"OBSIDIAN_VAULT_PATH": "/path/to/your/vault",
"OBSIDIAN_API_TOKEN": "your_api_token",
"OBSIDIAN_API_PORT": "27123"
}
}
}
}
Option 2: Source Installation Configuration
{
"mcpServers": {
"obsidian-mcp": {
"command": "node",
"args": ["/path/to/obsidian-mcp/build/index.js"],
"env": {
"OBSIDIAN_VAULT_PATH": "/path/to/your/vault",
"OBSIDIAN_API_TOKEN": "your_api_token",
"OBSIDIAN_API_PORT": "27123"
}
}
}
}
Option 3: Docker Installation Configuration
{
"mcpServers": {
"obsidian-mcp": {
"command": "docker",
"args": [
"exec",
"-i",
"obsidian-mcp-server",
"npm",
"start"
],
"env": {
"NODE_ENV": "production"
}
}
}
}
Note: For Docker, environment variables are configured in .env file or docker-compose.yml.
Environment Variables
| Variable | Description | Required | Default |
|---|---|---|---|
OBSIDIAN_VAULT_PATH |
Path to your Obsidian vault | β Yes | - |
OBSIDIAN_API_TOKEN |
Local REST API token | β Yes | - |
OBSIDIAN_API_PORT |
API port number | π§ Recommended | 27123 |
π§ For all configuration options, see Configuration Reference
π Prerequisites
- Node.js (v16 or higher)
- Obsidian Desktop Application
- Local REST API Plugin installed in Obsidian
Setting Up Obsidian Local REST API
- Install the "Local REST API" plugin in Obsidian
- Generate an API token in the plugin settings
- Note the port number (default: 27123)
- Ensure the plugin is enabled
π Documentation
- π Installation Guide - Complete installation instructions for all methods
- π§ Configuration Reference - Detailed configuration options and troubleshooting
- π οΈ API Documentation - Complete API reference for all 25 tools
- π Usage Examples - Practical examples and real-world scenarios
π€ Contributing
We welcome contributions! Please see our Contributing Guide for details.
Development Setup
git clone https://github.com/jianruidutong/obsidian-mcp.git
cd obsidian-mcp
npm install
npm run dev
π Troubleshooting
Common Issues
Connection refused error:
- Ensure Obsidian Local REST API plugin is installed and enabled
- Verify the API token and port number
- Check that Obsidian is running
Permission denied:
- Verify vault path permissions
- Ensure the API token has proper access rights
Environment variables not working:
- Use the
OBSIDIAN_prefix for all environment variables - Restart your MCP client after configuration changes
π For detailed troubleshooting, see Configuration Reference
π License
This project is licensed under the MIT License - see the LICENSE file for details.
π Acknowledgments
- Model Context Protocol by Anthropic
- Obsidian Local REST API plugin
- The original project address: https://github.com/newtype-01/obsidian-mcp
π Support
- π Report Issues
- π¬ Discussions
β Star this repository if you find it useful! β
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.
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.
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.
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.