Skip to content

Obsidian Brain

Local package path declaredNo credentials listedRepository declared by sourceUpdated 2026-05-16

io.github.sweir1/obsidian-brain · Registry status: active

Report data on this entry

At a glance

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

Vendor's own description, untranslated and unverified

Execution location
Local package path declaredMCP-Register · 2026-08-06
Required secrets declared
No credentials listedMCP-Register · 2026-08-06
Declared version and change
1.7.24 · Source-reported change date 2026-05-16MCP-Register · 2026-08-06
Repository as declared
github.com/sweir1/obsidian-brainMCP-Register · 2026-08-06
Configuration
can be built from the disclosed start template

Inspect connection paths and prerequisites

Related categories

6 of 15 categories. All categories in the segment catalogue

Page last changed:

Sources and collection
Runs
Local package path declared
Credentials
No credentials listed
Registry record changed
2026-05-16
Setup
Template available
Registry name
io.github.sweir1/obsidian-brain
Package coordinate
npm:obsidian-brain
Declared version
1.7.24
Source-reported listing date
2026-05-16
Source-reported change date
2026-05-16
First seen by tracevero
2026-08-06
Vendor's website
https://sweir1.github.io/obsidian-brain/

Evidence for this page: The values on this page come from several collections. Each row therefore states its own origin. What the confidence levels mean

Measured values

Measured values
Required secrets declaredNo credentials listed no
Original data – Required secret variables (raw): confirmed absent
Original data – Required secret headers (raw): confirmed absent
Source: MCP-Register · collected on 2026-08-06 · derived
Execution locationLocal package path declared local
Original data – Transports (raw): stdio
Source: MCP-Register · collected on 2026-08-06 · derived
Path argument presentyes
Original data – Path arguments (raw): confirmed absent
Original data – Path environment variables (raw): OBSIDIAN_BRAIN_CONFIG_DIR
Source: MCP-Register · collected on 2026-08-16 · derived
Repository URL listedRepository declared by source yes
Original data – Repository (raw): https://github.com/sweir1/obsidian-brain
Source: MCP-Register · collected on 2026-08-06 · derived
Field of use, derived from the vendor descriptionMemory
Original data – Description (raw): Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Source: MCP-Register · collected on 2026-08-26 · derived
Field of use, derived from the vendor descriptionKnowledge
Original data – Description (raw): Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Source: MCP-Register · collected on 2026-08-26 · derived
Declared version1.7.24
Source: MCP-Register · collected on 2026-08-06 · self-declared

What is measured is what a manifest declares, not what a piece of software does. This registry fetches no repository URL, no endpoint and no package index; nothing here is verified. Which value comes from which source, and by which rule it was formed, is set out in the Methodology.

Source data25

Evidence for this page: The values on this page come from several collections. Each row therefore states its own origin.

Raw values
Description (raw)Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Source: MCP-Register · collected on 2026-08-26 · self-declared
Environment variables (raw)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
Source: MCP-Register · collected on 2026-08-06 · self-declared
Required secret variables (raw)confirmed absent
Source: MCP-Register · collected on 2026-08-06 · self-declared
Transports (raw)stdio
Source: MCP-Register · collected on 2026-08-06 · self-declared
Path arguments (raw)confirmed absent
Source: MCP-Register · collected on 2026-08-06 · self-declared
Repository (raw)https://github.com/sweir1/obsidian-brain
Source: MCP-Register · collected on 2026-08-06 · self-declared
Package registries (raw)npm
Source: MCP-Register · collected on 2026-08-06 · self-declared
Required secret headers (raw)confirmed absent
Source: MCP-Register · collected on 2026-08-16 · self-declared
Path environment variables (raw)OBSIDIAN_BRAIN_CONFIG_DIR
Source: MCP-Register · collected on 2026-08-16 · self-declared
Remote URLs (raw)confirmed absent
Source: MCP-Register · collected on 2026-08-16 · self-declared
Remote hosts (raw)confirmed absent
Source: MCP-Register · collected on 2026-08-16 · self-declared
Registry status message (raw)confirmed absent
Source: MCP-Register · collected on 2026-08-16 · self-declared
First listed in the registry (raw)2026-05-16
Source: MCP-Register · collected on 2026-08-16 · self-declared
Last changed in the registry (raw)2026-05-16
Source: MCP-Register · collected on 2026-08-16 · self-declared
Schema version of the raw record (raw)https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json
Source: MCP-Register · collected on 2026-08-16 · self-declared
Delivery form (raw)package
Source: MCP-Register · collected on 2026-08-16 · self-declared
Repository platform (raw)github
Source: MCP-Register · collected on 2026-08-16 · self-declared
Repository subfolder (raw)confirmed absent
Source: MCP-Register · collected on 2026-08-16 · self-declared
Package identifiers (raw)obsidian-brain
Source: MCP-Register · collected on 2026-08-16 · self-declared
Package versions (raw)1.7.24
Source: MCP-Register · collected on 2026-08-16 · self-declared
Runtime hints (raw)npx
Source: MCP-Register · collected on 2026-08-16 · self-declared
Environment variable formats (raw)filepath, number, string
Source: MCP-Register · collected on 2026-08-16 · self-declared
Environment variable descriptions (raw)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).
Source: MCP-Register · collected on 2026-08-16 · self-declared
Icon formats (raw)confirmed absent
Source: MCP-Register · collected on 2026-08-16 · self-declared
Connection paths (source structure){"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":[]}
Source: MCP-Register · collected on 2026-09-08 · self-declared
Embed this badge

Paste this line into a README of your own. The badge states how many values the registry holds for the entry and when it last looked, and it links back to this page.

tracevero: number of measured values and date of collection for this registry entry

[![tracevero: number of measured values and date of collection for this registry entry](https://tracevero.com/badge/mcp/io-github-sweir1-obsidian-brain.svg)](https://tracevero.com/mcp/io-github-sweir1-obsidian-brain)

The image is drawn again on every request, so it always reports the current state while the pasted line stays as it is. It carries no rating and no traffic light – only the two measured figures.

Changes

Changes
2026-09-08Connection paths (source structure): – → {"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":[]}
2026-08-26Field of use, derived from the vendor description: – → Memory, Knowledge
2026-08-26Description (raw): – → Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.

These are the 3 most recent changes to this entry. Full history

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