Obsidian MCP Server

Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders. That is what the obsidian mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

This project implements a Model Context Protocol (MCP) server for connecting AI models with Obsidian knowledge bases. Through this server, AI models can directly access and manipulate Obsidian notes, including reading, creating, updating, and deleting notes, as well as managing folder structures.

• 🔗 Seamless Obsidian Integration — Direct access to Obsidian knowledge bases through MCP protocol
• 📝 Complete Note Management — Read, create, update, and delete notes with advanced text replacement
• 📁 Folder Operations — Create, rename, move, and delete folders with full hierarchy support
• 🔍 Intelligent Search — Full-text search across all file types with smart scoring
• 🤖 AI-Powered Analysis — NEW Strategic insights using TRILEMMA-PRINCIPLES framework
• 🔗 Auto Backlink Generation — NEW Intelligent detection and conversion of note names to wikilinks

What it needs from you

Configuration is passed through the environment: OBSIDIAN_VAULT_PATH, OBSIDIAN_API_TOKEN, OBSIDIAN_API_PORT, VAULT_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

• Node.js (v16 or higher) - Obsidian desktop application - Obsidian Local REST API plugin (needs to be installed in Obsidian)

Getting it running

@huangyihe/obsidian-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. It is maintained by newtype-01; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.