Obsidian Brain
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
{
"mcpServers": {
"obsidian-brain": {
"command": "npx",
"args": [
"-y",
"obsidian-brain"
],
"env": {
"VAULT_PATH": "<vault_path>",
"DATA_DIR": "<data_dir>",
"EMBEDDING_PRESET": "english",
"EMBEDDING_MODEL": "<embedding_model>",
"EMBEDDING_PROVIDER": "transformers",
"OLLAMA_BASE_URL": "http://localhost:11434",
"OLLAMA_EMBEDDING_DIM": "<ollama_embedding_dim>",
"OLLAMA_NUM_CTX": "<ollama_num_ctx>",
"OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL": "<obsidian_brain_ollama_auto_pull>",
"OBSIDIAN_BRAIN_NO_WATCH": "<obsidian_brain_no_watch>",
"OBSIDIAN_BRAIN_NO_CATCHUP": "<obsidian_brain_no_catchup>",
"OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MS": "3000",
"OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MS": "60000",
"OBSIDIAN_BRAIN_TOOL_TIMEOUT_MS": "30000",
"OBSIDIAN_BRAIN_MAX_CHUNK_TOKENS": "<obsidian_brain_max_chunk_tokens>",
"OBSIDIAN_BRAIN_CONFIG_DIR": "<obsidian_brain_config_dir>",
"OBSIDIAN_BRAIN_DEBUG": "<obsidian_brain_debug>"
}
}
}
}{
"mcpServers": {
"obsidian-brain": {
"command": "npx",
"args": [
"-y",
"obsidian-brain"
],
"env": {
"VAULT_PATH": "<vault_path>",
"DATA_DIR": "<data_dir>",
"EMBEDDING_PRESET": "english",
"EMBEDDING_MODEL": "<embedding_model>",
"EMBEDDING_PROVIDER": "transformers",
"OLLAMA_BASE_URL": "http://localhost:11434",
"OLLAMA_EMBEDDING_DIM": "<ollama_embedding_dim>",
"OLLAMA_NUM_CTX": "<ollama_num_ctx>",
"OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL": "<obsidian_brain_ollama_auto_pull>",
"OBSIDIAN_BRAIN_NO_WATCH": "<obsidian_brain_no_watch>",
"OBSIDIAN_BRAIN_NO_CATCHUP": "<obsidian_brain_no_catchup>",
"OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MS": "3000",
"OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MS": "60000",
"OBSIDIAN_BRAIN_TOOL_TIMEOUT_MS": "30000",
"OBSIDIAN_BRAIN_MAX_CHUNK_TOKENS": "<obsidian_brain_max_chunk_tokens>",
"OBSIDIAN_BRAIN_CONFIG_DIR": "<obsidian_brain_config_dir>",
"OBSIDIAN_BRAIN_DEBUG": "<obsidian_brain_debug>"
}
}
}
}npx -y obsidian-brainVAULT_PATHAbsolute path to your Obsidian vault (or any folder of .md files).
DATA_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. Default 8192. Ollama's own default is 2048 which silently truncates long chunks for models trained on larger contexts (nomic-embed-text at 8192, bge-m3 at 8192, qwen3-embedding:0.6b at 32 768). See https://github.com/ollama/ollama/issues/7008.
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 and fall back to the actionable error path (`HTTP 404 — try: ollama pull <model>`).
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.
AI-powered news intelligence — 21 tools for personalized monitoring, briefings, and semantic search
BuyWhere MCP server for product search, price comparison, and affiliate-ready shopping workflows.
Search and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.