Seekstone Obsidian Mcp Server

MCP开发工具

提供方 shaqmughal

开发工具 未标注 API Key 社区 / 第三方 ClaudeCursorCodexZed

Seekstone is a filesystem-direct Obsidian MCP server that gives Claude (and any MCP client) direct read/write access to your Obsidian vault — straight from the filesystem. No running Obsidian instance, no REST API plugin, no proxy.

一句话选型结论

按资料字段整理

Seekstone Obsidian Mcp Server 属于开发工具类 MCP 服务器,传输方式未标注,API Key,可直接接入 Claude、Cursor、Codex 等,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式未标注 鉴权API Key 部署方式未标注
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

obsidian mcp claude knowledge base knowledge management pkm note taking notes

支持客户端

适用场景

obsidianmcpclaude

安装与配置

未标注 API Key
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 已适配 Claude、Cursor、Codex,换客户端不用重新研究配置。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 使用前要准备好API Key对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Seekstone Obsidian Mcp Server当前 未标注 未标注 未标注 无 未标注
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方shaqmughal上游标注的维护方 shaqmughal
分类开发工具本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式API Key远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · Cross-platform本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

37.2 KB
来自项目仓库与上游目录的原文,未做删改

The Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window.

Filesystem-direct · single-digit-ms keyword search · ~26 ms semantic · ~2 KB payloads · 25 tools · macOS · Linux · Windows

seekstone.dev →


Seekstone obsidian-mcp-server (#1 by downloads) REST-proxy servers
Local REST API plugin Not needed Required Required
Obsidian app running Not needed — works with Obsidian closed Required Required
Search payload @ 10k notes 2.0 KB 47 KB up to 95 MB
Warm search latency @ 10k notes 5.6 ms 732 ms (~131× slower) up to 1,550 ms
Structured frontmatter queries Built-in (query_notes) — property/date/size predicates, answers in a few hundred bytes JSONLogic via REST Varies

Same queries, same committed vaults, 20 runs each, one machine. In-process adapters were re-run on the fixture-v2 vault in September 2026; the REST-proxy rows (rest, obsidian-mcp-server, mcp-obsidian) plus obsidian-mcp and obsidian-mcp-pro are June 2026 captures on fixture v1 — per-row provenance in benchmarks.json, the generated source of truth every number here is checked against in CI — full results across eight servers and three vault sizes below, fully reproducible from the harness.



What is Seekstone?

Seekstone is an Obsidian MCP server — it gives Claude (and any Model Context Protocol client) direct read and write access to your Obsidian vault. No Obsidian app needs to be open, no plugins are required, and nothing leaves your machine.

It reads your vault directly from disk rather than routing through the Obsidian Local REST API plugin, and holds a warm full-text index in-process. The practical difference is twofold:

  • Speed. Keyword searches return in single-digit milliseconds warm and semantic searches in ~26 ms — up to ~508× faster than every other Obsidian MCP server we benchmarked, because there's no subprocess to spawn and no HTTP round-trip per query.
  • Context. A broad search that returns tens of megabytes and millions of tokens via a REST-proxy server returns ~2 KB via Seekstone — up to a ~47,000× reduction that only widens as your vault grows.

Search comes in three modes: ranked full-text search (fuzzy and prefix matching), optional local semantic search (meaning-based, via a small on-device embedding model — opt-in, offline at runtime after a one-time ~30 MB model download), and structured metadata queries — query_notes filters by frontmatter properties (status, due, type, …), tags, folder, modified time, and size, answering questions like "which draft notes changed this week?" in a few hundred bytes instead of a search-and-read loop.

Claude can search and read your entire note library, in milliseconds, without burning most of its context window on a single tool call.

Published on npm as seekstone — install with npx -y seekstone. (Previously also published as obsidian-mcp-seekstone; that alias is deprecated but existing installs keep working.)


Why Seekstone? The numbers.

Most Obsidian MCP servers return full note content for every search hit. On a broad query that's megabytes of text your LLM has to process — most of it irrelevant, all of it burning context window.

Seekstone returns short ranked excerpts instead (~120 characters by default, tunable per query). We benchmarked Seekstone against 7 other Obsidian MCP servers — 8 servers total — across three vault sizes — 1,000 / 5,000 / 10,000 notes (20 runs each). Every number below is fully reproducible: the vaults are committed to this repo (generated from the public-domain 1911 Encyclopædia Britannica), so you can clone it and run the exact same benchmark yourself.

The point of testing three sizes is that this is where the architectures diverge — a real vault only grows.

Search payload — bytes returned per query (context tax; lower is better)

Server Architecture 1k notes 5k notes 10k notes
🥇 Seekstone in-process index 1.6 KB 1.8 KB 2.0 KB
mcpvault fs-direct subprocess 1.7 KB 1.9 KB 2.2 KB
obsidian-mcp-rs fs-direct, per-query scan 5.4 KB 5.8 KB 6.2 KB
obsidian-tc SQLite platform 4.6 KB 6.8 KB 7.3 KB
obsidian-mcp-server REST API 55 KB 47 KB 47 KB
obsidian-mcp-pro fs-direct subprocess 25 KB 84 KB 114 KB
obsidian-mcp fs-direct subprocess 18 KB 105 KB 203 KB
mcp-obsidian REST API 9.8 MB 45 MB 95 MB

Seekstone stays flat (~2 KB) no matter how big your vault gets, because it always returns ranked excerpts — and it's now the smallest payload of every server tested, edging out mcpvault at all three sizes. The REST-proxy servers return full note content for every match, so they grow with the vault — mcp-obsidian hits 95 MB at 10k notes, and a single broad query (the capital of) averaged 370.9 MB / 97.8 million tokens per call across 20 runs. At 10k notes that's a ~47,000× context-tax difference.

Search latency — warm mean, ms (lower is better)

Server 1k notes 5k notes 10k notes vs Seekstone @10k
🥇 Seekstone 1.0 2.8 5.6 —
obsidian-mcp-rs 6.0 19 36 ~6× slower
obsidian-mcp-pro 41 200 407 ~73× slower
obsidian-mcp-server 82 356 732 ~131× slower
obsidian-mcp 78 380 772 ~138× slower
mcpvault 90 431 893 ~159× slower
mcp-obsidian 164 740 1,550 ~277× slower
obsidian-tc 273 1,380 2,849 ~508× slower

Every competitor spawns a subprocess or makes HTTP round-trips per query, and most do work that scales with vault size. Seekstone holds a warm in-process index — no IPC, no network — so keyword search stays in single-digit milliseconds even at 10,000 notes (the shipped semantic pipeline — embed, scan, MaxSim rerank — lands at ~26 ms). And the gap widens with scale: from 1k → 10k notes the competitors slow down 5–10×, while Seekstone barely moves. Even the fastest alternative — obsidian-mcp-rs, which re-scans the vault on every query — is ~6× slower warm at 10k notes with 3× the payload, and the REST-proxy generation runs ~100–280× slower.

Tool list — tokens loaded before the first call (lower is better)

When a session starts, most MCP clients load the server's tool list (each tool's name, description, and input schema) into the model's context, before any tool is called. Some, such as Claude Code with tool search, load only the names until a tool is needed. Loaded in full, Seekstone's 25 tools cost ~5,742 tokens (26 KB). With SEEKSTONE_READ_ONLY=1 the 11 write tools drop out of the list and it falls to ~3,261 tokens, 43% less. The harness measures this from the built server over MCP (npm run harness -- schema-tax), and CI re-measures it on every commit, so a change to any tool's description or schema fails the build until the published number is updated.

Seekstone is the only server in our benchmark set that delivers both ~2 KB payloads and single-digit-ms keyword latency at every vault size — and, as far as we know, the only Obsidian MCP server with published, reproducible benchmarks. The harness, the synthetic vaults, and the full results are open source: see benchmark-scaling.md and the harness. Clone, run, verify.


Install

Choose the method that suits you best.

Using an AI agent? Paste this prompt

If you use Claude Code, Cursor, or another coding agent, you don't need to follow any instructions yourself — paste this prompt and the agent does the install:

> Install the seekstone MCP server for this editor. Run npx -y seekstone init --client code --write (use desktop, cursor, or vscode for other clients). It auto-detects my Obsidian vault; if it lists several, ask me which one and re-run with --vault "". Relay any errors to me, then tell me to restart this session so the seekstone tools load.

seekstone init is fully non-interactive — with --write it validates the vault and patches the client config in one shot (Claude Code via claude mcp add, other clients via an additive JSON patch with a timestamped backup).

Option 1 — One-click (Claude Desktop, no terminal needed)

  1. Download seekstone.mcpb (direct link, always the latest release)
  2. Open it with Claude Desktop — double-click in Finder, or right-click → Open With → Claude Desktop
  3. Pick your Obsidian vault folder when prompted

You'll know it worked when seekstone appears in Claude's toolbar. No JSON editing, no terminal, no Node.js required.

Want semantic search? Grab seekstone-semantic.mcpb instead — same server with the local embedding model shipped inside the bundle (~28 MB bigger), so meaning-based search works out of the box: still no terminal, and nothing is downloaded at runtime.

Option 2 — Guided setup (recommended for CLI users)

Open Terminal (macOS: Cmd+Space, type "Terminal", press Enter) and run:```bash
npx -y seekstone init


You'll know it worked when Seekstone appears in Claude's toolbar under the plug icon.

Seekstone reads Obsidian's own vault registry to detect your vault, validates it, and either prints the config block to paste or patches Claude Desktop directly:```bash
# Auto-detect vault, print config to paste
npx -y seekstone init

# Auto-detect vault, patch Claude Desktop in place (with backup)
npx -y seekstone init --write

# Specify vault explicitly if you have multiple
npx -y seekstone init --vault "/path/to/vault"

# Auto-configure Claude Code in one step (auto-detects vault, runs claude mcp add)
npx -y seekstone init --client code --write

# Or just print the Claude Code command without running it
npx -y seekstone init --client code

Option 3 — Manual config (Claude Desktop)

Add to claude_desktop_config.json (Settings → Developer → Edit Config):```json
{
"mcpServers": {
"seekstone": {
"command": "npx",
"args": ["-y", "seekstone"],
"env": { "SEEKSTONE_VAULT": "/absolute/path/to/your/vault" }
}
}
}


### Option 4 — Claude Code

Auto-detects your vault and configures Claude Code in one command:```bash
npx -y seekstone init --client code --write

Or manually, if you prefer to specify the vault path explicitly:```bash
claude mcp add seekstone --env SEEKSTONE_VAULT=/absolute/path/to/your/vault -- npx -y seekstone


### Option 5 — Cursor

One-click:  — then set `SEEKSTONE_VAULT` to your vault's absolute path in Cursor's MCP settings (the link installs a placeholder).

Or let the CLI auto-detect your vault and patch `~/.cursor/mcp.json` (with a backup):```bash
npx -y seekstone init --client cursor --write

Or add the block manually to ~/.cursor/mcp.json (global) or /.cursor/mcp.json (per-project):```json
{
"mcpServers": {
"seekstone": {
"command": "npx",
"args": ["-y", "seekstone"],
"env": { "SEEKSTONE_VAULT": "/absolute/path/to/your/vault" }
}
}
}


### Option 6 — VS Code

One-click:  — then set `SEEKSTONE_VAULT` to your vault's absolute path when VS Code opens the server config (the link installs a placeholder).

Or let the CLI auto-detect your vault and write the workspace config (`.vscode/mcp.json` in the current directory):```bash
npx -y seekstone init --client vscode --write

Or add it from the terminal:```bash
code --add-mcp '{"name":"seekstone","command":"npx","args":["-y","seekstone"],"env":{"SEEKSTONE_VAULT":"/absolute/path/to/your/vault"}}'


Or add the block manually to `.vscode/mcp.json` (workspace) or via Command Palette → *MCP: Open User Configuration* (user-global). Note VS Code's two quirks: the top-level key is `servers` (not `mcpServers`), and `"type": "stdio"` is required:```json
{
  "servers": {
    "seekstone": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "seekstone"],
      "env": { "SEEKSTONE_VAULT": "/absolute/path/to/your/vault" }
    }
  }
}

Requires VS Code 1.102+; seekstone appears in Copilot Chat's Agent mode tools picker.

Other MCP clients (Windsurf, Cline, …)

Seekstone is a standard MCP stdio server — any MCP client can run it. Use the same JSON block as above in your client's MCP config (command: npx, args: ["-y", "seekstone"], env SEEKSTONE_VAULT).


After installing, restart the client. On startup Seekstone walks the vault, builds an in-memory full-text index (a few seconds for thousands of notes), and keeps it live as you edit. The 25 tools below are then available to Claude.

Requires Node.js ≥ 22 for the CLI options. The one-click .mcpb bundle has no external requirements.

If Seekstone saves you context, consider ⭐ starring the repo — it helps others find it.


What can Claude do with your vault?

Once Seekstone is connected, you can ask Claude things like:

  • "Search my notes for everything about [topic] and give me a summary" — uses search, returns ranked excerpts, not full files
  • "Find all notes tagged #project and list their titles" — uses list_notes with a tag filter
  • "What's still open across my daily notes this week?" — uses list_tasks, returns one compact row per checkbox instead of whole notes; update_task checks one off with a single-character edit
  • "Read just the 'Decisions' section of my [project] note" — uses read_note with a section selector, so only that slice enters context
  • "What links to my [topic] note, and what does it link out to?" — uses get_backlinks and get_links to walk your graph
  • "Append today's standup notes to my daily note" — uses append_periodic_note, resolving the daily-note path from your vault config (Obsidian doesn't need to be open)
  • "Fix every occurrence of the old project name in this note" — uses replace_in_note, with a dry-run preview before it writes
  • "Add a summary section to the bottom of [note]" — uses append_note, never touches frontmatter
  • "Move all notes in /inbox to /archive/[year]" — uses move_note
  • "Update the status field in this note's frontmatter to 'done'" — uses patch_frontmatter, preserves key order and quote style
  • "Create a new meeting note for today with a standard template" — uses create_note

Claude never sees your full vault at once — it searches and reads selectively, so even large vaults (10k+ notes) stay within context budget.


Tools

Read

Tool Description
search Full-text search. Returns ranked excerpts (default ~120 chars, tunable via excerptLength), not full notes. Fuzzy and prefix matching; with SEEKSTONE_SEMANTIC=1, mode: "semantic"/"hybrid" searches by meaning via a local embedding model (nothing leaves your machine).
query_notes Structured metadata query. Filter by frontmatter key/value predicates (eq, ne, contains, exists, missing, gt/gte/lt/lte), tag, folder, modified time, and size; sort and select the fields you need. Returns compact rows (path + title by default), not note content.
context_pack Answer-ready context for a natural-language question in one call, hard-capped at a byte budget (default 2 KB): ranked excerpts, linked neighbor notes with one-line summaries, and follow-up source paths — replaces a search → read → get_backlinks round-trip loop. Scopable by folder/tag and takes the same mode as search.
read_note Read the full content of a note by vault-relative path. Supports returning a single section, block, or line range.
read_notes Read up to 20 notes (or sections, blocks, line ranges) in one call under a total byte budget (default 16 KB). Over budget, each note is cut to a fair share and marked truncated; one bad path returns its own error without failing the batch.
list_notes List notes, optionally filtered by folder prefix or tag.
list_tags List all tags in the vault sorted by usage count (or alphabetically).
list_tasks List Markdown checkbox tasks as compact structured rows (path, line, state, text, nearest heading) — vault-wide or filtered by note, folder, tag, state, or modified time. Custom markers (- [/], - [-], …) are first-class single-char states.
outline_note Return a note's heading and block structure without its full content — cheap navigation before a targeted read.
get_backlinks Find all notes that link to a given note.
get_links List all outgoing wikilinks and markdown links from a note.
resolve_note Turn a note name, path, or frontmatter alias into its canonical vault path(s) — with provenance per match, all candidates when ambiguous, and did-you-mean suggestions when nothing matches.
get_periodic_note Read today's (or any date's) daily, weekly, monthly, quarterly, or yearly note — path resolved from your vault config, no Obsidian required.
list_writes Recent writes from the journal — seq, timestamp, tool, touched paths, and whether each is still undoable. Metadata only, never note content.

Write

Tool Description
create_note Create a note (optional frontmatter + body); parent directories are created automatically.
delete_note Move a note to the vault's .trash/ folder (Obsidian-compatible, restorable). Pass permanent: true to skip the trash — the write journal still lets undo_write restore it.
move_note Move or rename a note — wikilinks and markdown links in other notes that point at it are rewritten so nothing breaks (rewriteLinks: false to opt out); destination directories are created automatically.
rename_heading Rename a heading in a note — every [[note#heading]] wikilink and embed across the vault is rewritten so references keep working (aliases preserved, fenced code blocks left alone).
append_note Append text to a note body without touching frontmatter.
patch_frontmatter Set, update, or delete frontmatter keys without reordering existing keys or changing quote style.
patch_note Append, prepend, or replace text at a heading or block reference (createIfMissing to add the section) — frontmatter untouched.
replace_in_note Find and replace text in the note body — literal or regex, case sensitivity, whole-word matching, optional limit (replaces all occurrences by default), and a dry-run preview.
append_periodic_note Append to today's periodic note, creating it from a template if it doesn't yet exist.
update_task Set one checkbox's state by path + line (from list_tasks) — rewrites exactly one character, leaving every other byte untouched. An expectText guard refuses if the task text changed since it was listed.
undo_write Revert a journaled write: every file it touched goes back to its byte-identical pre-write state (a multi-file move or heading rename is restored whole; a delete is restored even if it was permanent). Defaults to the most recent write; refuses with undo_conflict if a file changed since, unless force: true. The undo is itself journaled — undo_write({ seq }) on the undo entry redoes it.

Every write tool (append_note, patch_note, patch_frontmatter, replace_in_note, rename_heading, move_note, delete_note, append_periodic_note, update_task, and create_note with overwrite: true) supports optional compare-and-swap: pass the contentHash you got from read_note as prevHash and the call fails cleanly if the note changed underneath you — no silently discarded concurrent edit, no moving or deleting content you haven't seen. Every mutating result returns the new contentHash, so chained edits need no re-reads.

Every write is reversible. Before any write tool changes a byte, it journals the pre-image of every file it is about to touch under /.seekstone/history/ — content-addressed (identical states are stored once) and fsync'd before the vault write commits. list_writes shows the journal; undo_write restores byte-identically: a multi-file move_note or rename_heading is restored whole (the note and every link rewrite), and a delete_note comes back even if it was permanent. An undo after an external edit is refused with a structured undo_conflict unless you pass force: true — and even then the clobbered state is journaled first, so nothing is ever lost. Undo is itself journaled: repeated default undos walk backwards through the history, and undo_write({ seq }) on an undo entry redoes it. .seekstone/ is excluded from indexing and search like .trash/; add it to your vault's .gitignore. This complements git and Obsidian's File Recovery rather than replacing them — it is the recovery path the agent can drive.

Every write leaves a receipt. Set SEEKSTONE_AUDIT_FILE and every write-tool call — successful or refused — appends one JSON line: tool, vault-relative paths, sha-256 before/after, outcome (ok, hash_conflict, undo_conflict, policy_denied, error), and op metadata such as replacement counts or the .trash/ destination — never note content, frontmatter values, or search queries, so the file is safe to attach to a bug report.```jsonl
{"v":1,"ts":"2026-08-29T21:02:11.042Z","tool":"replace_in_note","outcome":"ok","durationMs":1.8,"seq":42,"files":[{"path":"notes/a.md","hashBefore":"3f9c…","hashAfter":"b71e…"}],"path":"notes/a.md","replacements":3}


The hashes are the same `contentHash` values `read_note` returns, so any record can be checked against the vault; `seq` is the journal entry the call committed, so a row indexes straight into `list_writes` / `undo_write`. Records are appended and fsync'd after the vault write commits, the file rotates to `.1` past `SEEKSTONE_AUDIT_MAX_SIZE`, an unwritable audit path fails boot, and a failed append reports the call as a structured `audit_failed` error rather than a clean success. A few `jq` recipes:```bash
jq -r '[.tool, .outcome] | @tsv' audit.jsonl | sort | uniq -c            # session summary by tool + outcome
jq -c 'select(.files[]?.path == "notes/a.md")' audit.jsonl              # history of one note
jq -c 'select(.ts > "2026-08-29T21:00:00Z" and .outcome == "ok")' audit.jsonl   # what changed since a timestamp

Fast and complete. Seekstone is the only Obsidian MCP server in our benchmark set to expose list_tags, outline_note, get_backlinks, and get_links as first-class tools. Four more capabilities set it apart:

  • Local semantic search, fully in-process. With SEEKSTONE_SEMANTIC=1, search and context_pack gain mode: "semantic" and "hybrid" — meaning-based retrieval through a small on-device embedding model (one-time npx -y seekstone fetch-model download, or the seekstone-semantic.mcpb bundle which ships the model inside; the running server never touches the network), with a MaxSim late-interaction rerank on top since 0.17.0. On our committed 10k-note benchmark vault (150-query golden set, fixture v2), the default model — measured end-to-end through the real search tool — scores 83.3% overall hit@5, 86.7% on the held-out split (vs 34.7% for keyword search alone) at ~26 ms warm p50, and the opt-in potion-retrieval-32M model (SEEKSTONE_SEMANTIC_MODEL; ~129 MB) reaches 86.7% overall hit@5, 86.7% held-out at ~55 ms. No other server we benchmarked ships offline, zero-native-dependency embeddings — and we measured the alternatives head-to-head on the same golden set, same run, committed dev/holdout split (committed comparison, read-out in COMPETITORS-SHA-322): obsidian-tc's plain Ollama-backed semantic search edges us on the held-out split (90.0% vs our 86.7%) at 169 ms/query and a 30-minute index vs our ~28 s, and its GraphRAG mode scores highest of anything we benchmarked (95.0% held-out), paying for it with seconds-per-query latency (2.9 s p50, 4.2 s p95 — against our 26–55 ms), ~8× the payload (16 KB vs ~2 KB per query), and a second server (Ollama + a 137M-parameter model) you must install and run. We pre-registered a gate to claim the #1 spot (GATE-V2-SHA-316, run on fixture v1) and missed it — that verdict is published with the same prominence a win would have been; no new gate ran on v2, and the same clauses recompute to the same miss. obsidian-mcp-pro could not index the 10k-note vault at all (its JSON vector store exceeds JavaScript's string limit after ~17 minutes of embedding). Pick your trade — the numbers are all committed.

  • Periodic notes, filesystem-direct. get_periodic_note and append_periodic_note resolve daily, weekly, monthly, quarterly, and yearly note paths by reading your vault's own config (.obsidian/daily-notes.json and the Periodic Notes plugin) — with Obsidian closed. Every REST-based server can only do this while the app is running.

  • Byte-identical frontmatter, guaranteed. patch_frontmatter edits YAML in place — preserving key order, quote style, and comments — and write-safety is proven byte-for-byte by the test harness. No other server we surveyed makes this guarantee.
  • Zero coupling. No Obsidian app, no Local REST API plugin, no plugin-version drift. Just your files on disk.

Configuration

Variable · Required · Description
SEEKSTONE_VAULT · Yes · Absolute path to your Obsidian vault.
SEEKSTONE_LOG_LEVEL · No · error \ · warn \ · info (default) \ · debug.
SEEKSTONE_LOG_FILE · No · Absolute path; when set, JSON-line logs are appended here (size-rotated).
SEEKSTONE_LOG_MAX_SIZE · No · Log-rotation threshold for SEEKSTONE_LOG_FILE (e.g. 10mb; default 5 MB).
SEEKSTONE_WATCH_POLL · No · Set to 1 to stat-poll for changes instead of native OS events — slower but reliable on network drives, WSL, and some containers.
SEEKSTONE_WATCH_POLL_INTERVAL · No · Stat-poll interval in ms (default 10000). Only used with SEEKSTONE_WATCH_POLL=1. Lower = faster pickup of external edits, higher CPU; raise it on slow network/9p mounts.
SEEKSTONE_READ_ONLY · No · Set to 1 to run read-only: the 11 write tools are unregistered from the tool list entirely (and rejected if called anyway), so the session provably cannot modify your vault.
SEEKSTONE_WRITE_PATHS · No · Comma-separated vault-relative globs (e.g. journal/**,inbox/*.md). Writes are permitted only under matching paths; the rest of the vault stays read-only.
SEEKSTONE_HISTORY · No · Set to 0 to disable the write journal (default on). With it on, every write tool stores the pre-image of each file it touches under /.seekstone/history/ so undo_write can restore it byte-for-byte.
SEEKSTONE_HISTORY_MAX_SIZE · No · Cap on stored pre-images (e.g. 100mb; default 50 MB). Oldest entries are evicted first and then show undoable: false in list_writes — never silently.
SEEKSTONE_HISTORY_MAX_ENTRIES · No · Cap on journal entries (default 1000); the oldest are dropped past it.
SEEKSTONE_AUDIT_FILE · No · Absolute path; off unless set. Appends one JSON-line audit record per write-tool call — ok or refused — with the tool, paths, sha-256 before/after, outcome, and op metadata. Never note content.
SEEKSTONE_AUDIT_MAX_SIZE · No · Rotate the audit file to .1 past this size (e.g. 10mb; default 10 MB).
SEEKSTONE_SEMANTIC · No · Set to 1 to enable semantic search (search and context_pack gain mode: "semantic" and "hybrid"). Requires the local embedding model — download it once with npx -y seekstone fetch-model; the running server never touches the network. The seekstone-semantic.mcpb bundle sets this automatically and ships the model inside.
SEEKSTONE_SEMANTIC_MODEL · No · Which local model to load: potion-base-8M (default, ~30 MB, 256-dim) or potion-retrieval-32M (~129 MB, 512-dim — more accurate on description-style queries at roughly 2× the query latency). Fetch it first with npx -y seekstone fetch-model --model potion-retrieval-32M.
SEEKSTONE_MODEL_PATH · No · Directory holding the Model2Vec embedding model (default: where fetch-model puts the selected model, under the cache dir).
SEEKSTONE_CACHE_DIR · No · Cache root for the downloaded model and per-vault embedding caches (default ~/.cache/seekstone).
SEEKSTONE_BUNDLED_MODEL_DIR · No · Set by the seekstone-semantic.mcpb bundle's manifest — points at the sharded model files shipped inside the extension, which the server reassembles into the model directory at boot (disk-only, verified against the pinned SHA-256 hashes). Not usually set by hand.
SEEKSTONE_INSTRUCTIONS · No · Path to a file whose contents become the MCP server's instructions string (surfaced to clients alongside the tool list). A relative path resolves against the vault root. Read once at boot, trimmed, capped at 16 KB (truncated with a warning past that). Missing, unreadable, or empty after trim means no instructions — never a boot failure.


How it works

Seekstone walks the vault with fast-glob, parses each note's frontmatter (byte-aware, so writes can prove the frontmatter region is byte-identical pre- and post-write), and builds a MiniSearch full-text index in memory. Search returns short ranked excerpts rather than whole notes — that excerpt-not-document design is where the context-tax win comes from. A cross-platform file watcher (chokidar) keeps the index current as you edit in Obsidian.

Writes are conservative by design: append_note never touches frontmatter, and patch_frontmatter edits the YAML document in place rather than re-serializing it, preserving key order, quote style, and comments.

It's built to stay up. Seekstone is tested on macOS, Linux, and Windows in CI on every commit, its write tools are hardened against pathological (ReDoS) inputs, and a stray unhandled rejection is logged rather than crashed on — so your long-lived MCP session keeps its warm index instead of dropping out mid-conversation.

…(正文过长,页面只展示前面部分,完整内容见仓库)

常见问题

7 问
答案由本站依据条目字段整理,不引用上游原文
Seekstone Obsidian Mcp Server 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Seekstone Obsidian Mcp Server 怎么在 Claude、Cursor、Codex 里配置?

它的传输方式未标注,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Seekstone Obsidian Mcp Server 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Seekstone Obsidian Mcp Server 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

Seekstone Obsidian Mcp Server 支持哪些客户端?

资料标注支持 Claude、Cursor、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Seekstone Obsidian Mcp Server 能提供哪些能力?

资料显示能力标签包括 obsidian、mcp、claude、knowledge base、knowledge management、pkm。具体工具清单以官方文档为准。

Seekstone Obsidian Mcp Server 需要什么运行环境?

运行时为 Cross-platform。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。