Obsidian Brain
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Open the source (opens github.com) https://github.com/sweir1/obsidian-brain
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.sweir1.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
obsidian-brain@1.7.24
From the server's entry in the official MCP Registry
Settings it asks for
VAULT_PATHrequired · Absolute path to your Obsidian vault (or any folder of .md files).DATA_DIR· Where to store the SQLite index + embedding cache. Defaults to $XDG_DATA_HOME/obsidian-brain or ~/.local/share/obsidian-brain.EMBEDDING_PRESET· Preset name: english (default, bge-small-en-v1.5), english-fast, english-quality, multilingual, multilingual-quality, multilingual-ollama. Ignored when…EMBEDDING_MODEL· Power-user override: any transformers.js checkpoint or Ollama model id. Takes precedence over EMBEDDING_PRESET. Switching auto-reindexes.EMBEDDING_PROVIDER· Embedding backend. 'transformers' (local, default) or 'ollama' (requires a running Ollama server).OLLAMA_BASE_URL· Base URL of a local Ollama server. Only used when EMBEDDING_PROVIDER=ollama.OLLAMA_EMBEDDING_DIM· Override the embedding dimensionality when EMBEDDING_PROVIDER=ollama. If unset, the server probes the model on startup.OLLAMA_NUM_CTX· Override Ollama's num_ctx for embed requests. Leave UNSET to let obsidian-brain auto-detect via `/api/show`'s `context_length` (e.g. nomic-embed-text=2048…OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL· Auto-pull the configured Ollama model when /api/show returns 404 (model not present). Default ON — choosing an Ollama-backed preset is implicit consent to…OBSIDIAN_BRAIN_OLLAMA_BYOM_AUTO_PULL· Opt-in to auto-pull for BYOM (custom EMBEDDING_MODEL) Ollama models OUTSIDE Ollama's official `library/` namespace. Default OFF — third-party models (e.g…OBSIDIAN_BRAIN_NO_WATCH· Set to '1' to disable the live chokidar file watcher. Useful on SMB/NFS vaults where FSEvents/inotify don't fire reliably — fall back to running…OBSIDIAN_BRAIN_NO_CATCHUP· Set to '1' to skip the startup catchup reindex pass that picks up edits made while the server was down. The live file watcher still starts (via…
Related
-
second-brain-cloudflare
MCP serversOne memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.
git clone https://github.com/rahilp/second-brain-cloudflare.git -
seekstone
MCP serversThe Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window. Filesystem-direct: single-digit-ms keyword search, ~26 ms local semantic search, ~2 KB payloads, 25 tools.
git clone https://github.com/shaqmughal/seekstone.git -
enquire-mcp
MCP serversThe #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.
git clone https://github.com/oomkapwn/enquire-mcp.git -
second-brain-mcp
MCP serversSecond brain en Obsidian: notas, conceptos como nodos, resurfacing y salud del grafo. En castellano.
@toportal/second-brain-mcp@0.1.1 -
brain-mcp
MCP serversYour Obsidian vault as private, searchable memory for Claude, Cursor, Hermes and any MCP client
debawho-brain-mcp@0.5.2 -
second-brain-bridge
MCP serversSearch and reason over your Obsidian-style Markdown vault, right from ChatGPT.