About Obsidian MCP Lite
Obsidian MCP Lite is a TypeScript MCP server for interacting with Obsidian vaults. It supports file browsing, text search, and vault content edits through Obsidian's Local REST API.
Key features
- 01List vault and directory files
- 02Read file contents
- 03Search text in files
- 04Patch or append content
- 05Delete files
Use cases
- 01Browse files in an Obsidian vault
- 02Find text across vault files
- 03Update or append notes
- 04Remove vault files
MCP support
Exposes vault file listing, reading, searching, editing, and deletion capabilities to MCP clients, using the Obsidian Local REST API.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEObsidian MCP Lite
A TypeScript-based MCP server for Obsidian, providing a simple interface to interact with Obsidian vaults.
Features
- List files in vault
- List files in directory
- Get file contents
- Search specific texts from files
- Patch content
- Append content
- Delete files
Prerequisites
- Node.js >= 18.16.0
- Obsidian with Local REST API plugin installed
- Obsidian API key
Setup
# Install dependencies
pnpm install
# Build server
pnpm run build
Configuration
-
Copy
.env.exampleto.env:cp .env.example .env -
Edit
.envand set your Obsidian API key and host:OBSIDIAN_API_KEY=your-api-key-here OBSIDIAN_HOST=http://localhost:27123
Installation
To use with Cursor, add the following config:
{
"mcpServers": {
"obsidian-mcp-lite": {
"command": "node",
"args": [
"/path/to/obsidian-mcp-lite/dist/index.js"
],
"env": {
"OBSIDIAN_API_KEY": "your-api-key-here"
}
}
}
}
Debugging
Use the MCP Inspector:
npx @modelcontextprotocol/inspector -e OBSIDIAN_API_KEY=your-api-key-here node dist/index.js"
You will find a URL provided in the terminal. Open it and access to the debugging tool in the browser.
Comments
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.