mcpField
O
Obsidian MCP Server Enhanced

Obsidian MCP Server Enhanced

Local
github.com/labeverydayMemory & Knowledge21Updated 73w ago

About Obsidian MCP Server Enhanced

Obsidian MCP Server Enhanced is an MCP server that lets Amazon Q work with Obsidian vaults through the Local REST API plugin, without needing the Obsidian app open. It is aimed at users who want AI-assisted note management in Obsidian.

Key features

  1. 01Read, create, update, append and delete notes
  2. 02List files and folders in the vault
  3. 03Get the currently active file
  4. 04Create daily notes with predefined sections
  5. 05Create meeting notes from structured templates

Use cases

  1. 01Letting Amazon Q read or organize Obsidian notes
  2. 02Generating daily or meeting notes through an AI assistant

MCP support

Built with FastMCP, the project is an MCP server that exposes obsidian_* tools and prompt templates to MCP clients such as Amazon Q CLI.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Obsidian MCP Server Enhanced

Status: Phase 1 Complete

A Model Context Protocol (MCP) server for integrating Amazon Q with Obsidian.

Project Overview

This MCP server allows Amazon Q to interact with Obsidian vaults without requiring the Obsidian application to be open. It leverages the Obsidian Local REST API plugin to provide functionality for note management, search, and knowledge management.

Current Status

  • Phase 1 (Core Infrastructure): Complete
  • Basic file operations, search, and note templates are fully implemented
  • Built with FastMCP for seamless integration with Amazon Q
  • Uses decorator-based approach for prompt registration
  • Ready to begin Phase 2: Essential Features

Features

Currently Implemented
  • File Operations: Read, create, update, append to, and delete notes
  • Basic Folder Management: List files in folders
  • Search: Basic search functionality for notes
  • Daily Notes: Create daily notes with predefined sections
  • Meeting Notes: Create meeting notes with structured templates
Planned Features
  • Advanced Folder Management: Create, delete, rename, and move folders
  • Organization & Metadata: Manage tags, frontmatter, and file organization
  • Advanced Search & Discovery: Enhanced search by content, tags, and other criteria
  • Knowledge Management: Extract highlights, compile notes, and more
  • Search and Compile: Search for notes and compile information into a single note
  • Note Organization: Organize notes on specific topics with AI assistance

Getting Started

Prerequisites
  1. Obsidian: Install Obsidian and create a vault
  2. Local REST API Plugin: Install the Local REST API plugin in Obsidian
  3. Python 3.10+: Make sure you have Python 3.10 or newer installed
Installation
  1. Clone this repository:

    git clone https://github.com/yourusername/mcp-obsidian-enhanced.git
    cd mcp-obsidian-enhanced
    
  2. Create a virtual environment:

    python -m venv venv
    source venv/bin/activate  # On Windows: venv\Scripts\activate
    
  3. Install dependencies:

    pip install -e ".[dev]"
    
  4. Create a .env file with your Obsidian API configuration:

    OBSIDIAN_API_KEY=your_api_key_from_local_rest_api_plugin
    OBSIDIAN_HOST=127.0.0.1
    OBSIDIAN_PORT=27124
    
Integration with Amazon Q CLI

To integrate this MCP server with Amazon Q CLI, configure the MCP server in your AWS configuration:

  1. Create or update the file at ~/.aws/amazonq/mcp.json:
{
  "mcpServers": {
    "obsidian-mcp-server": {
        "command": "uv",
        "args": ["--directory", "/path/to/mcp-obsidian-enhanced", "run", "run_server.py"],
        "env": {},
        "disabled": false,
        "autoApprove": []
    }
  }
}
  1. Replace /path/to/mcp-obsidian-enhanced with the actual path to your repository.
Running the Server

Run the server with:

python run_server.py

To test with MCP Inspector:

npx @modelcontextprotocol/inspector uv --directory ./ "run" "run_server.py"

Available Tools

Tool NameDescription
obsidian_read_noteGet content of a note from your Obsidian vault
obsidian_create_noteCreate a new note in your Obsidian vault
obsidian_update_noteUpdate an existing note in your Obsidian vault
obsidian_append_noteAppend content to an existing note
obsidian_delete_noteDelete a note from your Obsidian vault
obsidian_list_filesList files and folders in your Obsidian vault
obsidian_get_active_fileGet the currently active file in Obsidian
obsidian_create_daily_noteCreate a daily note with predefined sections
Planned Tools (Phase 2)
Tool NameDescription
obsidian_searchSearch for notes in your Obsidian vault
obsidian_summarize_noteSummarize the content of a note
obsidian_search_and_compileSearch for notes and compile information
obsidian_organize_notesOrganize notes on a specific topic

Available Prompts

The server provides prompt templates using the decorator-based approach:

Meeting Notes
@mcp.prompt("meeting-notes")
async def meeting_notes_prompt(
    title: str,
    date: str = "",
    participants: str = "",
    folder: str = "Meetings",
    tags: List[str] = None
) -> Dict[str, Any]:
    """Create a meeting note with the given details."""
    # Implementation...
Create Note
@mcp.prompt("create-note")
async def create_note_prompt(
    title: str,
    content: str,
    folder: str = "",
    tags: List[str] = None
) -> Dict[str, Any]:
    """Create a new note with the given details."""
    # Implementation...
Organize Notes
@mcp.prompt("organize-notes")
async def organize_notes_prompt(
    topic: str,
    folder: str = ""
) -> Dict[str, Any]:
    """Organize notes related to a specific topic."""
    # Implementation...

Configuration Options

Environment VariableDescriptionDefault
OBSIDIAN_API_KEYAPI key from Local REST API plugin(Required)
OBSIDIAN_HOSTHost where Obsidian is running127.0.0.1
OBSIDIAN_PORTPort for the API27124
OBSIDIAN_PROTOCOLProtocol to usehttps
OBSIDIAN_VERIFY_SSLWhether to verify SSL certificatesfalse
OBSIDIAN_TIMEOUTConnection timeout in seconds10
LOG_LEVELLogging level (INFO, DEBUG, etc.)INFO

Implementation Roadmap

Phase 1: Core Infrastructure (Complete)
  • ✅ Basic server setup with FastMCP
  • ✅ Configuration management
  • ✅ Obsidian API client
  • ✅ Basic file operations
  • ✅ Basic folder management tools
Phase 2: Essential Features (Planned)
  • Advanced search functionality
  • Metadata management
  • Improved templates
  • Note organization capabilities
  • Search and compile functionality
  • Note summarization
Phase 3: Advanced Features (Planned)
  • Knowledge management tools
  • Bulk operations
  • Advanced search capabilities
Phase 4: Optimization & Polish (Planned)
  • Performance optimizations
  • Enhanced error handling
  • Comprehensive logging
  • Detailed documentation

Testing the API Directly

You can test the Obsidian Local REST API endpoints directly using curl:

List Files in a Folder
curl -X GET "http://127.0.0.1:27124/vault/FolderName?list=true" \
  -H "Authorization: Bearer YOUR_API_KEY"
Read a Note
curl -X GET "http://127.0.0.1:27124/vault/path/to/note.md" \
  -H "Authorization: Bearer YOUR_API_KEY"
Create/Update a Note
curl -X PUT "http://127.0.0.1:27124/vault/path/to/note.md" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: text/markdown" \
  -d "# Note Title\n\nNote content here."
Search Notes
curl -X POST "http://127.0.0.1:27124/search/simple" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "query=search_term"

Contributing

Contributions are welcome! Please see the CONTRIBUTING.md file for guidelines.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.