obsidian-brain

A standalone Node MCP server that gives Claude (and any other MCP client) semantic search + knowledge graph + vault editing over an Obsidian vault. Runs as one local stdio process — no plugin, no HTTP bridge, no API key, nothing hosted. Your vault content never leaves your machine.

📖 Full docs → sweir1.github.io/obsidian-brain Companion plugin → sweir1/obsidian-brain-plugin (optional — unlocks active_note, dataview_query, base_query)

Contents — Why · Quick start · What you get · How it works · Companion plugin · Troubleshooting · Recent releases

Why obsidian-brain?

• Works without Obsidian running — unlike Local REST API-based servers, obsidian-brain reads .md files directly from disk. Obsidian can be closed; your vault is just a folder.

• No Local REST API plugin required — nothing to install inside Obsidian for the core experience.

• Chunk-level semantic search with RRF hybrid retrieval — embeddings at markdown-heading granularity, fused with FTS5 BM25 via Reciprocal Rank Fusion. Finds the exact chunk, ranks on meaning.

• The only Obsidian MCP server with PageRank + Louvain + graph analytics — ask for your vault's most influential notes, bridging notes, theme clusters. Nobody else ships this.

• Ollama provider for high-quality local embeddings — switch to qwen3-embedding:0.6b, nomic-embed-text, bge-m3, etc. with one env var.

• All in one npx install — no clone, no build, no API key, no hosted endpoint. Vault content never leaves your machine.

Related MCP server: mcp-markdown-vault

Quick start

One-line install (macOS + Claude Desktop)

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/sweir1/obsidian-brain/main/scripts/install.sh)"

Installs Homebrew + Node 20+ if you don't already have them, adds the /usr/local/bin symlinks that Claude Desktop needs, merges obsidian-brain into your claude_desktop_config.json, opens the Full Disk Access pane for you to toggle Claude on, and relaunches Claude. You'll be asked for your macOS password once (for Homebrew + the symlinks) and your vault path once. Everything else is automatic. Audit what it does: scripts/install.sh.

Manual install

Requires Node 20+ and an Obsidian vault (or any folder of .md files — Obsidian itself is optional).

Wire obsidian-brain into your MCP client. Example for Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "obsidian-brain": {
      "command": "npx",
      "args": ["-y", "obsidian-brain@latest", "server"],
      "env": { "VAULT_PATH": "/absolute/path/to/your/vault" }
    }
  }
}

Quit Claude Desktop (⌘Q on macOS) and relaunch. That's it.

For every other MCP client (Claude Code, Cursor, VS Code, Jan, Windsurf, Cline, Zed, LM Studio, JetBrains AI, Opencode, Codex CLI, Gemini CLI, Warp): see Install in your MCP client.

→ Full env-var reference: Configuration → Model / preset / Ollama details: Embedding model → Migrating from aaronsb's plugin: Migration guide

What you get

18 MCP tools grouped by intent:

• Find & read — search, list_notes, read_note

• Understand the graph — find_connections, find_path_between, detect_themes, rank_notes

• Write — create_note, edit_note, apply_edit_preview, link_notes, move_note, delete_note

• Live editor (requires companion plugin) — active_note, dataview_query, base_query

• Maintenance — reindex, index_status

→ Arguments, examples, and response shapes: Tool reference

How it works

flowchart LR
    Client["<b>MCP Client</b><br/>Claude Desktop · Claude Code<br/>Cursor · Jan · Windsurf · ..."]

    subgraph OB ["obsidian-brain (Node process)"]
        direction TB
        SQL["<b>SQLite index</b><br/>nodes · edges<br/>FTS5 · vec0 embeddings"]
        Vault["<b>Vault on disk</b><br/>your .md files"]
        Vault -->|"parse + embed"| SQL
        SQL -.->|"writes"| Vault
    end

    Client <-->|"stdio JSON-RPC"| OB

Retrieval and writes both go through a SQLite index: reads are microsecond-cheap, writes land on disk immediately and incrementally re-index the affected file. Embeddings are chunk-level (heading-aware recursive chunker preserving code + LaTeX blocks), and search's default hybrid mode fuses chunk-level semantic rank with FTS5 BM25 via Reciprocal Rank Fusion.

→ Deeper write-up — why stdio, why SQLite, why local embeddings: Architecture → Live watcher behaviour + debounces: Live updates → Scheduled reindex (macOS launchd / Linux systemd): Scheduled indexing (macOS) · (Linux)

Companion plugin (optional)

An optional Obsidian plugin at sweir1/obsidian-brain-plugin exposes live Obsidian runtime state — active editor, Dataview results, Bases rows — over a localhost HTTP endpoint. When installed and Obsidian is running, active_note, dataview_query, and base_query light up. Install via BRAT with repo ID sweir1/obsidian-brain-plugin.

Ship plugin and server at the same major.minor — server v1.7.x pairs with plugin v1.7.x. Patch-version drift is fine.

→ Security model, capability handshake, Dataview / Bases feature coverage: Companion plugin

Troubleshooting

Four most common:

• "Connector has no tools available" in Claude Desktop — usually the server crashed at startup. Check ~/Library/Logs/Claude/mcp-server-obsidian-brain.log. Fix: npm install -g obsidian-brain@latest, quit Claude (⌘Q), relaunch.

• ERR_DLOPEN_FAILED / NODE_MODULE_VERSION mismatch — better-sqlite3 built against a different Node ABI. Fix: PATH=/opt/homebrew/bin:$PATH npm rebuild -g better-sqlite3.

• Vault path not configured — VAULT_PATH is unset. Set it in the env block of your client config or shell.

• Old version loading via npx (your client still shows the previous release after a publish) — stale npx cache. Fix: rm -rf ~/.npm/_npx, then restart your client. Keeping @latest in your config prevents this.

→ Full troubleshooting guide (watcher not firing, stale index, running multiple clients, timeouts, embedding-dim mismatch, log locations): docs/troubleshooting.md

Recent releases

• v1.7.24 (2026-05-16) — embeddings.md BYOM callout + 5 devDep bumps

• v1.7.23 (2026-05-16) — BYOM Ollama auto-pull gate + logger sweep + SIGTERM unit test

• v1.7.22 (2026-05-15) — structured stderr (NDJSON) + Ollama preparing-state + dependabot security bumps + SIGTERM drain integration test

• v1.7.21 (2026-04-27) — install.sh vault-picker fix + auto ollama pull + docs/test polish

• v1.7.20 (2026-04-27) — Ollama prefix-lookup bug + 13 audit polish items

→ Full changelog: docs/CHANGELOG.md · Forward plan: docs/roadmap.md · Build from source: docs/development.md

Credits

Thanks to obra/knowledge-graph and aaronsb/obsidian-mcp-plugin for the ideas and code this project draws on. Also Xenova/transformers.js (local embeddings), graphology (graph analytics), and sqlite-vec (vector search in SQLite).

Related projects

• apple-notes-brain — sibling MCP server for Apple Notes on macOS: read, write, and search with full Markdown round-trip in both directions.

License

Apache License 2.0 — Copyright 2026 sweir1.