加载中…
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Obsidian Brain 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 67/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 Obsidian Brain 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
npx -y obsidian-brain@1.7.24运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-05-16T15:24:45.386473Z",
"publishedAt": "2026-05-16T15:24:45.386473Z",
"statusChangedAt": "2026-05-16T15:24:45.386473Z"
}
},
"server": {
"name": "io.github.sweir1/obsidian-brain",
"title": "Obsidian Brain",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.7.24",
"packages": [
{
"version": "1.7.24",
"transport": {
"type": "stdio"
},
"identifier": "obsidian-brain",
"runtimeHint": "npx",
"registryType": "npm",
"packageArguments": [
{
"type": "positional",
"value": "server"
}
],
"runtimeArguments": [
{
"type": "positional",
"value": "-y"
}
],
"environmentVariables": [
{
"name": "VAULT_PATH",
"format": "string",
"isRequired": true,
"description": "Absolute path to your Obsidian vault (or any folder of .md files)."
},
{
"name": "DATA_DIR",
"format": "string",
"description": "Where to store the SQLite index + embedding cache. Defaults to $XDG_DATA_HOME/obsidian-brain or ~/.local/share/obsidian-brain."
},
{
"name": "EMBEDDING_PRESET",
"format": "string",
"choices": [
"english",
"english-fast",
"english-quality",
"multilingual",
"multilingual-quality",
"multilingual-ollama"
],
"default": "english",
"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."
},
{
"name": "EMBEDDING_MODEL",
"format": "string",
"description": "Power-user override: any transformers.js checkpoint or Ollama model id. Takes precedence over EMBEDDING_PRESET. Switching auto-reindexes."
},
{
"name": "EMBEDDING_PROVIDER",
"format": "string",
"choices": [
"transformers",
"ollama"
],
"default": "transformers",
"description": "Embedding backend. 'transformers' (local, default) or 'ollama' (requires a running Ollama server)."
},
{
"name": "OLLAMA_BASE_URL",
"format": "string",
"default": "http://localhost:11434",
"description": "Base URL of a local Ollama server. Only used when EMBEDDING_PROVIDER=ollama."
},
{
"name": "OLLAMA_EMBEDDING_DIM",
"format": "number",
"description": "Override the embedding dimensionality when EMBEDDING_PROVIDER=ollama. If unset, the server probes the model on startup."
},
{
"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."
},
{
"name": "OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL",
"format": "string",
"choices": [
"",
"0",
"1"
],
"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>`)."
},
{
"name": "OBSIDIAN_BRAIN_OLLAMA_BYOM_AUTO_PULL",
"format": "string",
"choices": [
"",
"0",
"1"
],
"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."
},
{
"name": "OBSIDIAN_BRAIN_NO_WATCH",
"format": "string",
"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)."
},
{
"name": "OBSIDIAN_BRAIN_NO_CATCHUP",
"format": "string",
"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."
},
{
"name": "OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MS",
"format": "number",
"default": "3000",
"description": "Per-file reindex debounce for the live watcher, in milliseconds."
},
{
"name": "OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MS",
"format": "number",
"default": "60000",
"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."
},
{
"name": "OBSIDIAN_BRAIN_TOOL_TIMEOUT_MS",
"format": "number",
"default": "30000",
"description": "Per-tool-call timeout in milliseconds. Tools exceeding this return an MCP error instead of hanging."
},
{
"name": "OBSIDIAN_BRAIN_MAX_CHUNK_TOKENS",
"format": "number",
"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."
},
{
"name": "OBSIDIAN_BRAIN_CONFIG_DIR",
"format": "filepath",
"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."
},
{
"name": "OBSIDIAN_BRAIN_DEBUG",
"format": "string",
"choices": [
"",
"1"
],
"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."
},
{
"name": "OBSIDIAN_BRAIN_LOG_FORMAT",
"format": "string",
"choices": [
"",
"ndjson"
],
"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."
}
]
}
],
"repository": {
"url": "https://github.com/sweir1/obsidian-brain",
"source": "github"
},
"websiteUrl": "https://sweir1.github.io/obsidian-brain/",
"description": "Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required."
}
}