Obsidian Mcp Server

What is Obsidian MCP Server?

A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your Obsidian vault. It allows you to access notes, create content, manage tags, and search your knowledge base through natural conversation.

How to use Obsidian MCP Server?

Run the server via npx with the VAULT_PATH environment variable, or deploy with Docker. It exposes an SSE endpoint (port 3000 by default) that MCP clients like Claude Desktop or Cursor can connect to using mcp-remote. Configure the server in your AI assistant’s MCP settings pointing to the SSE URL.

Key features of Obsidian MCP Server

• CRUD operations for notes with write modes (overwrite/append/prepend)
• Frontmatter parsing and tag management with auditing
• Full‑text search, backlinks, and broken‑link detection
• Section‑level read, append, and replace operations
• Optional compact response mode (40‑60% smaller payloads)
• SSE transport for remote access without local installation

Use cases of Obsidian MCP Server

• Ask an AI assistant to find notes by tag or full‑text search
• Create, update, or delete notes and directories through conversation
• Automate tag audits and bulk find‑and‑replace across the vault
• Detect broken wiki‑links and list backlinks for a given note
• Reorganize vault structure by moving or duplicating notes

FAQ from Obsidian MCP Server

What dependencies does Obsidian MCP Server require?

It requires Node.js 18 or later and read/write access to an Obsidian vault (Markdown files). The server is built on Express.js and uses the gray‑matter library for YAML frontmatter.

Where does the server store data?

It reads and writes directly to the vault directory you mount at startup. No external database is used; all data lives in your existing .md files.

Is authentication supported?

Yes, the server supports optional API key authentication. When API_KEY is set, all /sse and /message endpoints require a Bearer token or api_key query parameter. The /health endpoint remains public.

What transport does the server use?

It uses Server‑Sent Events (SSE) for real‑time communication. Clients connect to /sse and can send messages via POST to /message. A direct MCP call endpoint is also available at /sse (POST).

Are there any known limits or performance considerations?

The server offers a compact response mode to reduce token usage. For large vaults, using get-notes-info instead of reading content improves efficiency. Full read/write access to the vault means caution is needed; delete operations require confirmation.