MCP Obsidian
Enables semantic search across Obsidian vaults using vector embeddings and ChromaDB. Supports multiple vaults with real-time indexing and provides both MCP server and CLI interfaces for natural language querying of notes.
README
mcp-obsidian
An MCP (Model Context Protocol) server for semantic search in Obsidian vaults using embedded ChromaDB vector storage. I intend on keeping this fairly minimal to keep usage with Claude simple.
Features
- 🔍 Semantic search across your Obsidian vaults using vector embeddings
- 📅 Temporal search to find notes by modification date with optional semantic filtering
- 📁 Support for multiple vault configurations
- 🔄 Real-time monitoring with automatic re-indexing after file change
- 🔁 Manual re-indexing on demand via the
reindex_vaultstool - 🚀 Fast, incremental updates with ChromaDB backend
- 🔒 Thread-safe operations for concurrent access
- 🔧 Works as both MCP server and CLI tool
Prerequisites
- Python 3.10 or higher
- uv package manager
Installation
Install uv (if not already installed)
pip install uv
Install mcp-obsidian
Option 1: Install as a uv tool (Recommended)
uv tool install "git+https://github.com/alexhholmes/mcp-obsidian.git"
mcp-obsidian configure # Configure your vaults
Option 2: Install from source
- Clone the repository:
git clone https://github.com/yourusername/mcp-obsidian.git
cd mcp-obsidian
- Create and activate a virtual environment with uv:
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
- Install the package in development mode:
uv pip install -e .
This will install all dependencies including:
- questionary (interactive CLI)
- chromadb (vector database)
- langchain-text-splitters (document chunking)
- fastmcp (MCP server framework)
- watchdog (file system monitoring)
Configuration
Initial Setup
Configure your Obsidian vaults:
mcp-obsidian configure
This interactive command will:
- Prompt you to select vault directories
- Name each vault for easy reference
- Store configuration in
~/.mcp-obsidian/config.json
Manual Configuration
You can also manually edit ~/.mcp-obsidian/config.json:
{
"vaults": [
{
"name": "Personal Notes",
"path": "/path/to/your/obsidian/vault"
},
{
"name": "Work Docs",
"path": "/path/to/another/vault"
}
]
}
Usage
As an MCP Server
Run the server for use with MCP-compatible clients:
mcp-obsidian
The server exposes the following tools:
semantic_search: Search across all configured vaults using semantic similarity with optional vault filteringtemporal_search: Search notes by modification date with optional semantic filteringreindex_vaults: Manually trigger a re-index of all configured Obsidian vaults
The vectors are stored along with the following metadata, which can be used for filtering searches:
vault: The name of the vault containing the documenttitle: The filename without extensionsource: The relative path from the vault rootmodified: Unix timestamp of the file's last modification timefile_path: The absolute path to the source filestart_line/end_line: Line numbers for the chunk within the original documentchunk_index/total_chunks: Position of this chunk within the documentfile_hash: MD5 hash of the file content for change detection
CLI Usage
Search directly from the command line:
# Search all vaults
mcp-obsidian search "your search query"
# Search a specific vault
mcp-obsidian search "your search query" --vault "Personal Notes"
# Reconfigure vaults
mcp-obsidian configure
# Rebuild search index
mcp-obsidian index
Integration with Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"obsidian": {
"command": "mcp-obsidian"
}
}
}
or alternatively use to configuration tool to set it up automatically:
mcp-obsidian configure
How It Works
- Indexing: The server reads all markdown files from configured vaults and creates vector embeddings using ChromaDB
- Chunking: Large documents are split into smaller chunks using recursive character splitting for better search granularity
- Search: Queries are converted to embeddings and matched against the document database using cosine similarity
- File Watching: The server monitors vault directories for changes and automatically updates the index
License
MIT License
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。