Vault Cortex

Created By

aliasunder2 months ago

MCP server that exposes an Obsidian vault to any MCP client — no Obsidian plugins required. 26 tools + 3 prompts across vault CRUD, hybrid search (FTS5 + vector + cross-encoder reranking), task queries (Tasks-plugin + Dataview formats), structured memory (About Me/ files), link graph (backlinks, outgoing links, orphan detection), properties, and daily notes. Runs locally via Docker or remotely with Obsidian Sync + OAuth 2.1 on a VPS.

# obsidian

# vault

Overview Content Tools Comments

Overview

What is Vault Cortex?

Vault Cortex gives any MCP client — Claude Desktop, Claude Code, Cursor, OpenCode — full access to your Obsidian vault. Search notes, read and write content, query tasks, explore the link graph, manage structured memory, and resolve daily notes — all through 26 tools + 3 guided prompts over a single Docker container.

The typical Obsidian + MCP setup needs three moving parts running at once: Obsidian open → Local REST API plugin → a separate MCP server wrapping that API. vault-cortex replaces all of it with Docker and your vault folder.

Features

Plugin-free — Obsidian doesn't need to be running; the server works directly with .md files on disk, and headless Obsidian Sync keeps the vault current.
Remote access — use it from your phone, a remote server, or any MCP client via OAuth 2.1.
Hybrid search — FTS5 keyword matching + vector semantic similarity + cross-encoder reranking via RRF fusion. Keywords stay precise; vectors bridge vocabulary gaps; the reranker rescues intent-heavy queries.
Structured memory — dated entries with section targeting and auto-initialization, for persistent AI personalization.
Obsidian-native — understands frontmatter, wikilinks, tags, headings, and daily notes.
Task queries — vault-wide task index parsing both Tasks-plugin emoji and Dataview inline-field formats. Filter by status, dates, priority, folder, or heading.
Link graph — backlinks, outgoing links, and orphan detection.

Tools (26)

Vault CRUD — vault_read_note, vault_write_note, vault_patch_note, vault_replace_in_note, vault_delete_span, vault_list_notes, vault_delete_note, vault_move_note, vault_update_properties
Search — vault_search, vault_search_by_tag, vault_search_by_folder, vault_search_by_property, vault_recent_notes, vault_list_tags, vault_list_tasks, vault_list_property_keys, vault_list_property_values, vault_find_orphans, vault_get_backlinks, vault_get_outgoing_links
Memory — vault_get_memory, vault_update_memory, vault_delete_memory, vault_list_memory_files
Daily Notes — vault_get_daily_note

Prompts (3)

vault-orientation — surveys vault stats, folder distribution, property adoption, orphans, tags, recent notes, and the memory layer
memory-review — structural overview + dated timeline of the memory layer with guided reflection
daily-review — reviews a day's daily note with outgoing links, backlinks, and date-specific activity

Quick Start (local — one command)

Prerequisites: Docker, Node.js >= 20.12, and an Obsidian vault.

npx vault-cortex@latest init

Or manually — see the local guide or remote guide.

Authentication

OAuth 2.1 (Claude Desktop, Claude Code, claude.ai) — dynamic client registration, JWT access tokens, 60-day sliding refresh.
Static bearer (Claude Code, MCP Inspector, curl) — the raw MCP_AUTH_TOKEN.

Server Config

{
  "mcpServers": {
    "vault-cortex": {
      "url": "http://localhost:8000/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_MCP_AUTH_TOKEN>"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

Tavily Mcp

Serper MCP ServerA Serper MCP Server

DeepChatYour AI Partner on Desktop

MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs

WindsurfThe new purpose-built IDE to harness magic

Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.

Amap Maps高德地图官方 MCP Server