Zum Inhalt springen

Obsidian Brain

Lokaler Paketweg angegebenKeine Zugangsdaten angegebenRepository von der Quelle angegebenStand 2026-05-16

io.github.sweir1/obsidian-brain · Registerstatus: aktiv

Angaben zu diesem Eintrag melden

Auf einen Blick

Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.

Beschreibung des Anbieters, unübersetzt und ungeprüft

Ausführungsort
Lokaler Paketweg angegebenMCP-Register · 2026-08-06
Pflicht-Geheimnisse deklariert
Keine Zugangsdaten angegebenMCP-Register · 2026-08-06
Deklarierte Version und Änderung
1.7.24 · Änderung, von der Quelle gemeldet 2026-05-16MCP-Register · 2026-08-06
Repository laut Rohsatz
github.com/sweir1/obsidian-brainMCP-Register · 2026-08-06
Konfiguration
baubar aus der offengelegten Startvorlage

Verbindungswege und Voraussetzungen ansehen

Verwandte Kategorien

6 von 15 Kategorien. Alle Kategorien im Themenkatalog

Seite zuletzt geändert:

Quellen und Erhebung
Läuft
Lokaler Paketweg angegeben
Zugangsdaten
Keine Zugangsdaten angegeben
Im Register geändert
2026-05-16
Einrichtung
Vorlage vorhanden
Registername
io.github.sweir1/obsidian-brain
Paketkoordinate
npm:obsidian-brain
Deklarierte Version
1.7.24
Eintragung, von der Quelle gemeldet
2026-05-16
Änderung, von der Quelle gemeldet
2026-05-16
Von tracevero erstmals gesehen
2026-08-06
Homepage des Anbieters
https://sweir1.github.io/obsidian-brain/

Beleg dieser Seite: Die Werte dieser Seite stammen aus mehreren Erhebungen. Jede Zeile nennt ihre Herkunft deshalb selbst. Was die Vertrauensgrade bedeuten

Gemessene Werte

Gemessene Werte
Pflicht-Geheimnisse deklariertKeine Zugangsdaten angegeben nein
Originalangabe – Geheime Pflichtvariablen (Rohangabe): nachweislich nicht vorhanden
Originalangabe – Geheime Pflichtkopfzeilen (Rohangabe): nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-06 · abgeleitet
AusführungsortLokaler Paketweg angegeben lokal
Originalangabe – Transportarten (Rohangabe): stdio
Quelle: MCP-Register · erhoben am 2026-08-06 · abgeleitet
Pfadargument vorhandenja
Originalangabe – Pfadargumente (Rohangabe): nachweislich nicht vorhanden
Originalangabe – Pfad-Umgebungsvariablen (Rohangabe): OBSIDIAN_BRAIN_CONFIG_DIR
Quelle: MCP-Register · erhoben am 2026-08-16 · abgeleitet
Repository-Adresse geführtRepository von der Quelle angegeben ja
Originalangabe – Repository (Rohangabe): https://github.com/sweir1/obsidian-brain
Quelle: MCP-Register · erhoben am 2026-08-06 · abgeleitet
Einsatzgebiet, aus der Anbieterbeschreibung abgeleitetGedächtnis
Originalangabe – Beschreibung (Rohangabe): Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Quelle: MCP-Register · erhoben am 2026-08-26 · abgeleitet
Einsatzgebiet, aus der Anbieterbeschreibung abgeleitetWissen
Originalangabe – Beschreibung (Rohangabe): Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Quelle: MCP-Register · erhoben am 2026-08-26 · abgeleitet
Deklarierte Version1.7.24
Quelle: MCP-Register · erhoben am 2026-08-06 · Selbstauskunft

Gemessen ist, was ein Manifest erklärt, nicht was eine Software tut. Dieses Register ruft keine Repository-Adresse auf, keinen Endpunkt und keinen Paketindex; nichts hier ist nachgeprüft. Welche Angabe aus welcher Quelle stammt und nach welcher Regel sie gebildet ist, steht in der Methodik.

Daten der Quelle25

Beleg dieser Seite: Die Werte dieser Seite stammen aus mehreren Erhebungen. Jede Zeile nennt ihre Herkunft deshalb selbst.

Rohangaben
Beschreibung (Rohangabe)Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Quelle: MCP-Register · erhoben am 2026-08-26 · Selbstauskunft
Umgebungsvariablen (Rohangabe)VAULT_PATH, DATA_DIR, EMBEDDING_PRESET, EMBEDDING_MODEL, EMBEDDING_PROVIDER, OLLAMA_BASE_URL, OLLAMA_EMBEDDING_DIM, OLLAMA_NUM_CTX, OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL, OBSIDIAN_BRAIN_OLLAMA_BYOM_AUTO_PULL, OBSIDIAN_BRAIN_NO_WATCH, OBSIDIAN_BRAIN_NO_CATCHUP, OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MS, OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MS, OBSIDIAN_BRAIN_TOOL_TIMEOUT_MS, OBSIDIAN_BRAIN_MAX_CHUNK_TOKENS, OBSIDIAN_BRAIN_CONFIG_DIR, OBSIDIAN_BRAIN_DEBUG, OBSIDIAN_BRAIN_LOG_FORMAT
Quelle: MCP-Register · erhoben am 2026-08-06 · Selbstauskunft
Geheime Pflichtvariablen (Rohangabe)nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-06 · Selbstauskunft
Transportarten (Rohangabe)stdio
Quelle: MCP-Register · erhoben am 2026-08-06 · Selbstauskunft
Pfadargumente (Rohangabe)nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-06 · Selbstauskunft
Repository (Rohangabe)https://github.com/sweir1/obsidian-brain
Quelle: MCP-Register · erhoben am 2026-08-06 · Selbstauskunft
Paketquellen (Rohangabe)npm
Quelle: MCP-Register · erhoben am 2026-08-06 · Selbstauskunft
Geheime Pflichtkopfzeilen (Rohangabe)nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Pfad-Umgebungsvariablen (Rohangabe)OBSIDIAN_BRAIN_CONFIG_DIR
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Remote-Adressen (Rohangabe)nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Remote-Hosts (Rohangabe)nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Statusmeldung des Registers (Rohangabe)nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Im Register eingetragen am (Rohangabe)2026-05-16
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Im Register geändert am (Rohangabe)2026-05-16
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Schemafassung des Rohsatzes (Rohangabe)https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Bereitstellungsform (Rohangabe)paket
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Repository-Plattform (Rohangabe)github
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Repository-Unterordner (Rohangabe)nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Paketbezeichner (Rohangabe)obsidian-brain
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Paketversionen (Rohangabe)1.7.24
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Laufzeithinweise (Rohangabe)npx
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Formate der Umgebungsvariablen (Rohangabe)filepath, number, string
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Beschreibungen der Umgebungsvariablen (Rohangabe)DATA_DIR=Where to store the SQLite index + embedding cache. Defaults to $XDG_DATA_HOME/obsidian-brain or ~/.local/share/obsidian-brain. · EMBEDDING_MODEL=Power-user override: any transformers.js checkpoint or Ollama model id. Takes precedence over EMBEDDING_PRESET. Switching auto-reindexes. · EMBEDDING_PRESET=Preset name: english (default, bge-small-en-v1.5), english-fast, english-quality, multilingual, multilingual-quality, multilingual-ollama. Ignored when EMBEDDING_MODEL is set. · EMBEDDING_PROVIDER=Embedding backend. 'transformers' (local, default) or 'ollama' (requires a running Ollama server). · OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MS=Graph-wide community-detection (Louvain) debounce for the live watcher, in milliseconds. Louvain is the only expensive op — batching it prevents per-edit CPU spikes. · OBSIDIAN_BRAIN_CONFIG_DIR=Override the per-user config directory where obsidian-brain stores model overrides (`model-overrides.json`) and the user-fetched seed (`seed-models.json`). Default is `$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_DEBUG=Set 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_FORMAT=Set 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. · OBSIDIAN_BRAIN_MAX_CHUNK_TOKENS=Override 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_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 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_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 index` on a schedule (launchd/systemd). · 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 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_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. `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_TOOL_TIMEOUT_MS=Per-tool-call timeout in milliseconds. Tools exceeding this return an MCP error instead of hanging. · OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MS=Per-file reindex debounce for the live watcher, in milliseconds. · 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, 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. · VAULT_PATH=Absolute path to your Obsidian vault (or any folder of .md files).
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Symbolformate (Rohangabe)nachweislich nicht vorhanden
Quelle: MCP-Register · erhoben am 2026-08-16 · Selbstauskunft
Verbindungswege (Quellstruktur){"packages":[{"registryType":"npm","identifier":"obsidian-brain","version":"1.7.24","runtimeHint":"npx","transport":"stdio","environment":[{"name":"VAULT_PATH","description":"Absolute path to your Obsidian vault (or any folder of .md files).","format":"string","required":true,"secret":false},{"name":"DATA_DIR","description":"Where to store the SQLite index + embedding cache. Defaults to $XDG_DATA_HOME/obsidian-brain or ~/.local/share/obsidian-brain.","format":"string","required":false,"secret":false},{"name":"EMBEDDING_PRESET","description":"Preset name: english (default, bge-small-en-v1.5), english-fast, english-quality, multilingual, multilingual-quality, multilingual-ollama. Ignored when EMBEDDING_MODEL is set.","format":"string","required":false,"secret":false},{"name":"EMBEDDING_MODEL","description":"Power-user override: any transformers.js checkpoint or Ollama model id. Takes precedence over EMBEDDING_PRESET. Switching auto-reindexes.","format":"string","required":false,"secret":false},{"name":"EMBEDDING_PROVIDER","description":"Embedding backend. 'transformers' (local, default) or 'ollama' (requires a running Ollama server).","format":"string","required":false,"secret":false},{"name":"OLLAMA_BASE_URL","description":"Base URL of a local Ollama server. Only used when EMBEDDING_PROVIDER=ollama.","format":"string","required":false,"secret":false},{"name":"OLLAMA_EMBEDDING_DIM","description":"Override the embedding dimensionality when EMBEDDING_PROVIDER=ollama. If unset, the server probes the model on startup.","format":"number","required":false,"secret":false},{"name":"OLLAMA_NUM_CTX","description":"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, 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.","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL","description":"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 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>`).","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_OLLAMA_BYOM_AUTO_PULL","description":"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. `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.","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_NO_WATCH","description":"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 index` on a schedule (launchd/systemd).","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_NO_CATCHUP","description":"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 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.","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MS","description":"Per-file reindex debounce for the live watcher, in milliseconds.","format":"number","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MS","description":"Graph-wide community-detection (Louvain) debounce for the live watcher, in milliseconds. Louvain is the only expensive op — batching it prevents per-edit CPU spikes.","format":"number","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_TOOL_TIMEOUT_MS","description":"Per-tool-call timeout in milliseconds. Tools exceeding this return an MCP error instead of hanging.","format":"number","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_MAX_CHUNK_TOKENS","description":"Override 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.","format":"number","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_CONFIG_DIR","description":"Override 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.","format":"filepath","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_DEBUG","description":"Set 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.","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_LOG_FORMAT","description":"Set 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.","format":"string","required":false,"secret":false}],"additional_arguments_declared":true}],"remotes":[]}
Quelle: MCP-Register · erhoben am 2026-09-08 · Selbstauskunft
Abzeichen einbetten

Diese Zeile setzt das Abzeichen in eine eigene README-Datei. Es zeigt, wie viele Werte dieses Register zu dem Eintrag führt und wann es zuletzt nachgesehen hat, und es führt von dort auf diese Seite zurück.

tracevero: Zahl der gemessenen Werte und Erhebungstag zu diesem Registereintrag

[![tracevero: Zahl der gemessenen Werte und Erhebungstag zu diesem Registereintrag](https://tracevero.de/badge/mcp/io-github-sweir1-obsidian-brain.svg)](https://tracevero.de/mcp/io-github-sweir1-obsidian-brain)

Das Bild wird bei jedem Abruf neu gerechnet und nennt darum immer den heutigen Stand; die eingefügte Zeile bleibt unverändert. Es enthält keine Bewertung und keine Ampel – nur die beiden gemessenen Angaben.

Änderungen

Änderungen
2026-09-08Verbindungswege (Quellstruktur): – → {"packages":[{"registryType":"npm","identifier":"obsidian-brain","version":"1.7.24","runtimeHint":"npx","transport":"stdio","environment":[{"name":"VAULT_PATH","description":"Absolute path to your Obsidian vault (or any folder of .md files).","format":"string","required":true,"secret":false},{"name":"DATA_DIR","description":"Where to store the SQLite index + embedding cache. Defaults to $XDG_DATA_HOME/obsidian-brain or ~/.local/share/obsidian-brain.","format":"string","required":false,"secret":false},{"name":"EMBEDDING_PRESET","description":"Preset name: english (default, bge-small-en-v1.5), english-fast, english-quality, multilingual, multilingual-quality, multilingual-ollama. Ignored when EMBEDDING_MODEL is set.","format":"string","required":false,"secret":false},{"name":"EMBEDDING_MODEL","description":"Power-user override: any transformers.js checkpoint or Ollama model id. Takes precedence over EMBEDDING_PRESET. Switching auto-reindexes.","format":"string","required":false,"secret":false},{"name":"EMBEDDING_PROVIDER","description":"Embedding backend. 'transformers' (local, default) or 'ollama' (requires a running Ollama server).","format":"string","required":false,"secret":false},{"name":"OLLAMA_BASE_URL","description":"Base URL of a local Ollama server. Only used when EMBEDDING_PROVIDER=ollama.","format":"string","required":false,"secret":false},{"name":"OLLAMA_EMBEDDING_DIM","description":"Override the embedding dimensionality when EMBEDDING_PROVIDER=ollama. If unset, the server probes the model on startup.","format":"number","required":false,"secret":false},{"name":"OLLAMA_NUM_CTX","description":"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, 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.","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL","description":"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 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>`).","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_OLLAMA_BYOM_AUTO_PULL","description":"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. `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.","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_NO_WATCH","description":"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 index` on a schedule (launchd/systemd).","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_NO_CATCHUP","description":"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 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.","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MS","description":"Per-file reindex debounce for the live watcher, in milliseconds.","format":"number","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MS","description":"Graph-wide community-detection (Louvain) debounce for the live watcher, in milliseconds. Louvain is the only expensive op — batching it prevents per-edit CPU spikes.","format":"number","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_TOOL_TIMEOUT_MS","description":"Per-tool-call timeout in milliseconds. Tools exceeding this return an MCP error instead of hanging.","format":"number","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_MAX_CHUNK_TOKENS","description":"Override 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.","format":"number","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_CONFIG_DIR","description":"Override 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.","format":"filepath","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_DEBUG","description":"Set 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.","format":"string","required":false,"secret":false},{"name":"OBSIDIAN_BRAIN_LOG_FORMAT","description":"Set 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.","format":"string","required":false,"secret":false}],"additional_arguments_declared":true}],"remotes":[]}
2026-08-26Einsatzgebiet, aus der Anbieterbeschreibung abgeleitet: – → Gedächtnis, Wissen
2026-08-26Beschreibung (Rohangabe): – → Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.

Hier stehen die 3 jüngsten Änderungen dieses Eintrags. Vollständiger Verlauf

tracevero · https://tracevero.de/mcp/io-github-sweir1-obsidian-brain