What are the prerequisites for using Obsidian MCP REST Server?
You need Node.js 16 or higher, an Obsidian vault with the Local REST API plugin installed and configured, and a valid API key.
@PublikPrinciple
基本信息
An MCP server implementation for accessing Obsidian via local REST API
List all notes in the vault or a specific folder
Read the contents of a specific note
Create or update a note
Search for notes using a query string
Get metadata for a specific note
The Obsidian MCP REST Server is an MCP (Model Context Protocol) server implementation that provides access to Obsidian vaults through a local REST API. It allows AI assistants to interact with Obsidian notes and manage vault content via a standardized interface.
Install the package globally with npm install -g PublikPrinciple/obsidian-mcp-rest. Create a config.json file with your Obsidian Local REST API key, host, and port (default 27123), then start the server with obsidian-mcp-rest --config path/to/config.json. For Claude Desktop, add a server configuration in its MCP section using the same command and arguments.
You need Node.js 16 or higher, an Obsidian vault with the Local REST API plugin installed and configured, and a valid API key.
The server only runs locally, communicates via stdin/stdout, and requires no external network access. All requests to the Obsidian REST API are authenticated with your API key, keeping data local.
It provides five tools: `listNotes` (list notes/vault), `readNote` (read note content), `writeNote` (create/update note), `searchNotes` (search by query), and `getMetadata` (get note metadata).
Yes. Clone the repository, install dependencies, build, and then run `npm install -g .` to install globally, or resolve TypeScript errors by installing TypeScript globally.
In Claude Desktop settings, navigate to the MCP section and add a server configuration with `"name": "obsidian-mcp"`, `"command": "obsidian-mcp-rest"`, and `"args": ["--config", "path/to/config.json"]`.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.
评论