Obsidian Brain
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin…
- Pricing
- Open source
- Runs
- Locally
- Version
- 1.7.24
- Listing updated
- 4 days ago
About Obsidian Brain
Obsidian Brain is an open-source MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Install
Run in a terminal
claude mcp add obsidian-brain --env VAULT_PATH='<VAULT_PATH>' -- npx -y obsidian-brainAdd to claude_desktop_config.json
{
"mcpServers": {
"obsidian-brain": {
"command": "npx",
"args": [
"-y",
"obsidian-brain"
],
"env": {
"VAULT_PATH": "<VAULT_PATH>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"obsidian-brain": {
"command": "npx",
"args": [
"-y",
"obsidian-brain"
],
"env": {
"VAULT_PATH": "<VAULT_PATH>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"obsidian-brain": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"obsidian-brain"
],
"env": {
"VAULT_PATH": "<VAULT_PATH>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"obsidian-brain": {
"command": "npx",
"args": [
"-y",
"obsidian-brain"
],
"env": {
"VAULT_PATH": "<VAULT_PATH>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"obsidian-brain": {
"command": "npx",
"args": [
"-y",
"obsidian-brain"
],
"env": {
"VAULT_PATH": "<VAULT_PATH>"
}
}
}
}Configuration
VAULT_PATHAbsolute path to your Obsidian vault (or any folder of .md files).RequiredDATA_DIRWhere to store the SQLite index + embedding cache. Defaults to $XDG_DATA_HOME/obsidian-brain or ~/.local/share/obsidian-brain.EMBEDDING_PRESETPreset name: english (default, bge-small-en-v1.5), english-fast, english-quality, multilingual, multilingual-quality, multilingual-ollama. Ignored when EMBEDDING_MODEL is set.EMBEDDING_MODELPower-user override: any transformers.js checkpoint or Ollama model id. Takes precedence over EMBEDDING_PRESET. Switching auto-reindexes.EMBEDDING_PROVIDEREmbedding backend. 'transformers' (local, default) or 'ollama' (requires a running Ollama server).OLLAMA_BASE_URLBase URL of a local Ollama server. Only used when EMBEDDING_PROVIDER=ollama.OLLAMA_EMBEDDING_DIMOverride the embedding dimensionality when EMBEDDING_PROVIDER=ollama. If unset, the server probes the model on startup.OLLAMA_NUM_CTXOverride 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, bge-m3=8192, qwen3-embedding:0.6b=32 768). Setting this manually imposes a hard cap and may silently truncate longer inputs — see https://github.com/ollama/ollama/issues/14259. Ollama's own default is 2048 which truncates for any model trained on a larger context. See also https://github.com/ollama/ollama/issues/7008. Fallback when both env is unset AND /api/show is unreachable: 8192.OBSIDIAN_BRAIN_OLLAMA_AUTO_PULLAuto-pull the configured Ollama model when /api/show returns 404 (model not present). Default ON — choosing an Ollama-backed preset is implicit consent to download its model. Streams /api/pull progress to stderr. Set to '0' to disable auto-pull entirely (master kill-switch) and fall back to the actionable error path (`HTTP 404 — try: ollama pull <model>`).OBSIDIAN_BRAIN_OLLAMA_BYOM_AUTO_PULLOpt-in to auto-pull for BYOM (custom EMBEDDING_MODEL) Ollama models OUTSIDE Ollama's official `library/` namespace. Default OFF — third-party models (e.g. `user/custom-fork`, `myregistry.com/team/model`) require this env var to be set to `1` before they will auto-pull, to prevent silent downloads of arbitrary user-named artifacts. Preset-known models (via EMBEDDING_PRESET) and bare model ids in the official library (e.g. `qwen3-embedding:0.6b`, `library/llama3:8b`) continue to auto-pull by default per the existing OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL behavior.OBSIDIAN_BRAIN_NO_WATCHSet 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 index` on a schedule (launchd/systemd).OBSIDIAN_BRAIN_NO_CATCHUPSet 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 OBSIDIAN_BRAIN_NO_WATCH=1 to disable that separately), and first-time indexing on an empty DB is unaffected — this knob only governs the post-restart `enqueueBackgroundReindex` walk.OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MSPer-file reindex debounce for the live watcher, in milliseconds.OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MSGraph-wide community-detection (Louvain) debounce for the live watcher, in milliseconds. Louvain is the only expensive op — batching it prevents per-edit CPU spikes.OBSIDIAN_BRAIN_TOOL_TIMEOUT_MSPer-tool-call timeout in milliseconds. Tools exceeding this return an MCP error instead of hanging.OBSIDIAN_BRAIN_MAX_CHUNK_TOKENSOverride the adaptive chunk-size budget (in tokens). When set, this beats the capacity probed from the model's tokenizer or Ollama /api/show. Use for debugging or for models with stale tokenizer configs.OBSIDIAN_BRAIN_CONFIG_DIROverride the per-user config directory where obsidian-brain stores model overrides (`model-overrides.json`) and the user-fetched seed (`seed-models.json`). Default is `$XDG_CONFIG_HOME/obsidian-brain` on macOS/Linux (or `~/.config/obsidian-brain`) and `%APPDATA%/obsidian-brain` on Windows. Both files survive `npm update obsidian-brain` because they live outside the package.OBSIDIAN_BRAIN_DEBUGSet to "1" to print a verbose synchronous startup trace to stderr — every preflight, createContext, server.connect, and shutdown step is logged with a monotonic timestamp. The LAST line before any silent failure tells you exactly which step the server reached. No-op when unset (no overhead). Use to diagnose silent-crash failure modes.OBSIDIAN_BRAIN_LOG_FORMATSet to 'ndjson' for one-JSON-object-per-line stderr output (timestamp + level + message + structured fields). Default is human-readable plain text (`obsidian-brain: <message>`). Useful for piping logs into aggregators (Datadog, Loki, Vector, journald) that index structured fields.
Pricing
Open source
Prices change. Check sweir1.github.io before you buy.
Obsidian Brain FAQ
Is Obsidian Brain free?
Yes. Obsidian Brain is open source, so you can use and self-host it for free.
How do I add Obsidian Brain to Claude Code?
Run this command in your terminal: claude mcp add obsidian-brain --env VAULT_PATH='<VAULT_PATH>' -- npx -y obsidian-brain
What are the best alternatives to Obsidian Brain?
The closest alternatives to Obsidian Brain are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.
Alternatives to Obsidian Brain

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

Nautilus Compass Memory
MCP serverLocal-first long-term memory layer for AI agents, served over MCP
Not checked yet- 5 tools
- Remote
- Open source
- 1.3K GitHub stars
- Knowledge and memory

note1
MCP serverMCP server giving AI assistants search and summaries across your note1 meetings
- 4 tools
- Remote
- Free trial
- 1 GitHub star
- Productivity
MedXpert 图书馆连接器(通用版)
MCP serverLocal MCP server that searches and answers questions over your own Markdown wiki
Runs locally- 4 tools
- Open source
- Knowledge and memory