ObsidianReaderMCP

ObsidianReaderMCP

Enables AI assistants to manage Obsidian vaults via the local REST API, supporting CRUD operations, batch processing, templates, and vault analytics.

Category
访问服务器

README

ObsidianReaderMCP

GitHub Python MCP License

A comprehensive Python MCP (Model Context Protocol) server for managing Obsidian vaults through the obsidian-local-rest-api plugin.

Features

Core CRUD Operations

  • Create: Create new notes with content, metadata, and tags
  • Read: Retrieve note content and metadata by path
  • Update: Modify existing notes (content, metadata, tags)
  • Delete: Remove notes from the vault

Extended Functionality

  • Batch Operations: Create, update, or delete multiple notes at once
  • Template System: Create and use note templates with variables
  • Link Analysis: Analyze relationships between notes
  • Search & Filter: Advanced search by content, tags, date range, word count
  • Vault Statistics: Generate comprehensive vault analytics
  • Backup Management: Create and manage vault backups

MCP Server Integration

  • Full MCP protocol support for AI assistant integration
  • Async/await support for high performance
  • Comprehensive error handling and logging
  • Rate limiting and connection management

Installation

Prerequisites

  1. Obsidian with the obsidian-local-rest-api plugin installed and configured
  2. Python 3.10+

Method 1: Using uvx (Recommended)

The easiest way to use ObsidianReaderMCP is with uvx, which allows you to run it without installation:

# Run directly without installation
uvx obsidianreadermcp

# Or install as a tool
uv tool install obsidianreadermcp
obsidianreadermcp

Method 2: Using pip

# Install from PyPI
pip install obsidianreadermcp

# Run the server
obsidianreadermcp

Method 3: Install from Source

# Clone the repository
git clone https://github.com/QianJue-CN/ObsidianReaderMCP.git
cd ObsidianReaderMCP

# Install dependencies
uv sync

# Or with pip
pip install -e .

Configuration

Environment Variables

Create a .env file in the project root (copy from .env.example):

# Obsidian API Configuration
OBSIDIAN_HOST=localhost
OBSIDIAN_PORT=27123
OBSIDIAN_API_KEY=your_api_key_here
OBSIDIAN_USE_HTTPS=false
OBSIDIAN_TIMEOUT=30
OBSIDIAN_MAX_RETRIES=3
OBSIDIAN_RATE_LIMIT=10

# MCP Server Configuration
LOG_LEVEL=INFO
ENABLE_DEBUG=false

Obsidian Setup

  1. Install the obsidian-local-rest-api plugin from the Community Plugins
  2. Enable the plugin in Obsidian settings
  3. Configure the plugin:
    • Set API port (default: 27123)
    • Generate an API key
    • Enable CORS if needed
  4. Start the local REST API server

Usage

As a Python Library

import asyncio
from obsidianreadermcp import ObsidianClient
from obsidianreadermcp.config import ObsidianConfig
from obsidianreadermcp.models import NoteMetadata

async def main():
    # Create configuration
    config = ObsidianConfig()  # Uses environment variables

    # Create and connect client
    async with ObsidianClient(config) as client:
        # Create a note
        metadata = NoteMetadata(
            tags=["example", "demo"],
            frontmatter={"title": "My Note", "author": "Me"}
        )

        note = await client.create_note(
            path="my_note.md",
            content="# My Note\n\nThis is my note content.",
            metadata=metadata
        )

        # Read the note
        retrieved_note = await client.get_note("my_note.md")
        print(f"Note content: {retrieved_note.content}")

        # Update the note
        await client.update_note(
            path="my_note.md",
            content="# Updated Note\n\nThis content has been updated."
        )

        # Search notes
        results = await client.search_notes("updated")
        print(f"Found {len(results)} matching notes")

        # Delete the note
        await client.delete_note("my_note.md")

asyncio.run(main())

As an MCP Server

# Method 1: Using uvx (recommended)
uvx obsidianreadermcp

# Method 2: Using installed package
obsidianreadermcp

# Method 3: Using Python module
python -m obsidianreadermcp.server

# Method 4: Programmatically
python -c "
import asyncio
from obsidianreadermcp.server import main
asyncio.run(main())
"

Claude Desktop Integration

Add to your Claude Desktop configuration file:

{
  "mcpServers": {
    "obsidian": {
      "command": "uvx",
      "args": ["obsidianreadermcp"],
      "env": {
        "OBSIDIAN_HOST": "localhost",
        "OBSIDIAN_PORT": "27123",
        "OBSIDIAN_API_KEY": "your-api-key-here"
      }
    }
  }
}

Or if you have it installed globally:

{
  "mcpServers": {
    "obsidian": {
      "command": "obsidianreadermcp",
      "env": {
        "OBSIDIAN_HOST": "localhost",
        "OBSIDIAN_PORT": "27123",
        "OBSIDIAN_API_KEY": "your-api-key-here"
      }
    }
  }
}

Extended Features

from obsidianreadermcp.extensions import ObsidianExtensions

async with ObsidianClient(config) as client:
    extensions = ObsidianExtensions(client)

    # Create a template
    template = extensions.create_template(
        name="daily_note",
        content="# {{date}}\n\n## Tasks\n- {{task}}\n\n## Notes\n{{notes}}",
        description="Daily note template"
    )

    # Create note from template
    note = await extensions.create_note_from_template(
        template_name="daily_note",
        path="daily/2024-01-15.md",
        variables={
            "date": "2024-01-15",
            "task": "Review project status",
            "notes": "All systems operational"
        }
    )

    # Batch operations
    batch_notes = [
        {"path": "note1.md", "content": "Content 1", "tags": ["batch"]},
        {"path": "note2.md", "content": "Content 2", "tags": ["batch"]},
    ]
    result = await extensions.batch_create_notes(batch_notes)

    # Analyze vault
    stats = await extensions.generate_vault_stats()
    print(f"Vault has {stats.total_notes} notes with {stats.total_words} words")

    # Find orphaned notes
    orphaned = await extensions.find_orphaned_notes()
    print(f"Found {len(orphaned)} orphaned notes")

MCP Tools

When running as an MCP server, the following tools are available:

Core Operations

  • create_note: Create a new note with content and metadata
  • get_note: Retrieve a note by path
  • update_note: Update an existing note
  • delete_note: Delete a note
  • list_notes: List all notes in vault or folder
  • search_notes: Search notes by content

Vault Management

  • get_vault_info: Get vault information and statistics
  • get_tags: List all tags used in the vault
  • get_notes_by_tag: Find notes with specific tags

API Reference

ObsidianClient

The main client class for interacting with Obsidian.

Methods

  • async create_note(path: str, content: str = "", metadata: Optional[NoteMetadata] = None) -> Note
  • async get_note(path: str) -> Note
  • async update_note(path: str, content: Optional[str] = None, metadata: Optional[NoteMetadata] = None) -> Note
  • async delete_note(path: str) -> bool
  • async list_notes(folder: str = "") -> List[str]
  • async search_notes(query: str, limit: int = 50, context_length: int = 100) -> List[SearchResult]
  • async get_vault_info() -> VaultInfo
  • async get_tags() -> List[str]
  • async get_notes_by_tag(tag: str) -> List[Note]

ObsidianExtensions

Extended functionality for advanced vault management.

Methods

  • async batch_create_notes(notes_data: List[Dict], continue_on_error: bool = True) -> Dict
  • async batch_update_notes(updates: List[Dict], continue_on_error: bool = True) -> Dict
  • async batch_delete_notes(paths: List[str], continue_on_error: bool = True) -> Dict
  • create_template(name: str, content: str, variables: Optional[List[str]] = None, description: Optional[str] = None) -> Template
  • async create_note_from_template(template_name: str, path: str, variables: Optional[Dict[str, str]] = None, metadata: Optional[NoteMetadata] = None) -> Note
  • async create_backup(backup_path: str, include_attachments: bool = True) -> BackupInfo
  • async analyze_links() -> List[LinkInfo]
  • async find_orphaned_notes() -> List[str]
  • async find_broken_links() -> List[LinkInfo]
  • async generate_vault_stats() -> VaultStats
  • async search_by_date_range(start_date: Optional[datetime] = None, end_date: Optional[datetime] = None, date_field: str = "created") -> List[Note]
  • async search_by_word_count(min_words: Optional[int] = None, max_words: Optional[int] = None) -> List[Note]

Testing

Run the test suite:

# With uv
uv run pytest

# With pip
pytest

# With coverage
pytest --cov=obsidianreadermcp --cov-report=html

Examples

See the examples/ directory for more detailed usage examples:

  • basic_usage.py: Demonstrates core CRUD operations
  • advanced_features.py: Shows extended functionality
  • mcp_integration.py: MCP server integration examples

Contributing

We welcome contributions! Please see our Contributing Guidelines for details.

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Make your changes
  4. Add tests for new functionality
  5. Run the test suite (uv run pytest)
  6. Commit your changes (git commit -m 'Add some amazing feature')
  7. Push to the branch (git push origin feature/amazing-feature)
  8. Open a Pull Request

Issues and Support

License

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

Acknowledgments

Star History

Star History Chart

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选