swarmvault MCP — ユースケース, インストール & ライブデモ

なぜ使うのか

主な機能

30+ input formats: PDFs, docs, code, audio, video, transcripts, images
Typed knowledge graph with community detection and contradiction spotting
Hybrid search: SQLite FTS + semantic embeddings
Offline-capable via heuristic provider (no API keys required)
Installs across 12 agent platforms via swarmvault install --agent <name>

ライブデモ

実際の動作

swarmvault.replay ▶ 準備完了

0/0

インストール

クライアントを選択

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "swarmvault": {
      "command": "npx",
      "args": [
        "-y",
        "swarmvault"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "swarmvault": {
      "command": "npx",
      "args": [
        "-y",
        "swarmvault"
      ],
      "_inferred": true
    }
  }
}

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "swarmvault": {
      "command": "npx",
      "args": [
        "-y",
        "swarmvault"
      ],
      "_inferred": true
    }
  }
}

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "swarmvault": {
      "command": "npx",
      "args": [
        "-y",
        "swarmvault"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "swarmvault",
      "command": "npx",
      "args": [
        "-y",
        "swarmvault"
      ]
    }
  ]
}

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.config/zed/settings.json

{
  "context_servers": {
    "swarmvault": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "swarmvault"
        ]
      }
    }
  }
}

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add swarmvault -- npx -y swarmvault

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方： swarmvault

Compound research across months into a queryable wiki

👤 Researchers, analysts doing deep work over time ⏱ ~60 min intermediate

使うタイミング： You've been researching a topic for weeks and realize your notes are scattered.

前提条件

swarmvault CLI — npm install -g @swarmvaultai/cli
A vault — swarmvault init --obsidian --profile personal-research

フロー

Dump raw sources

Drop everything into raw/: PDFs, saved articles, meeting transcripts, code snippets.✓ コピーしました

→ Immutable raw/ folder populated
Compile the wiki

swarmvault compile — generate wiki/ with typed pages and link frontmatter.✓ コピーしました

→ Wiki pages created
Query through MCP

Via the MCP: what's the current consensus in my notes about 'post-quantum TLS timeline'? Include contradictions.✓ コピーしました

→ Answer with graph-walked citations and flagged contradictions

結果： A growing, queryable research base that gets smarter with every addition.

注意点

Noisy inputs produce noisy graph — Curate raw/ — delete junk instead of ingesting everything
Over-relying on the graph for 'truth' — Edges tagged 'inferred' or 'ambiguous' are hypotheses, not facts — respect the tags

組み合わせ： documentation-server

Turn meeting transcripts into structured team knowledge

👤 Teams doing a lot of recorded meetings ⏱ ~45 min intermediate

使うタイミング： You have Fathom/Otter transcripts piling up and want to query across them.

フロー

Drop transcripts in raw/

Copy all my Otter transcripts from last quarter into raw/meetings/.✓ コピーしました

→ Files in place
Compile

swarmvault compile. Confirm entities (people, projects) were extracted.✓ コピーしました

→ Entity count report
Query

What did we decide about the pricing overhaul across all Q1 meetings? Cite each source.✓ コピーしました

→ Consolidated answer with source transcripts cited

結果： Institutional memory that survives people leaving.

Build a book-club wiki with cross-book reasoning

👤 Serious readers ⏱ ~90 min intermediate

使うタイミング： You want the AI to reason across books, not just one at a time.

フロー

Ingest

Drop PDFs + notes for 5 books into raw/; compile.✓ コピーしました

→ Wiki with one page per book + concept pages
Cross-reason

Which concepts show up in 3+ books? Identify contradictions between authors.✓ コピーしました

→ Concept map with contradictions flagged

結果： A reading practice that compounds.

組み合わせ

他のMCPと組み合わせて10倍の力を

swarmvault + documentation-server

swarmvault for structured wiki; documentation-server for quick-ingest search

Ingest new papers into both — compare retrieval quality and structure.✓ コピーしました

swarmvault + logseq

Export vault pages into a Logseq graph

Export wiki/ Markdown into my Logseq pages/ dir with frontmatter preserved.✓ コピーしました

ツール

このMCPが提供する機能

ツール	入力	呼び出すタイミング	コスト
vault_search	query: str, top_k?: int	Main retrieval	free (local)
vault_get_page	slug: str	Full page read	free
vault_graph_neighbors	slug, depth?	Explore concept graph	free
vault_contradictions	topic?: str	Quality check	free
vault_compile	(none)	After adding new raw/	CPU + optional embedding calls
vault_graph_report	scope?: str	Overview of a topic	free

コストと制限

運用コスト

APIクォータ: Zero with the heuristic provider; otherwise your LLM provider's limits
呼び出しあたりのトークン: Compile can stream large source content through embeddings; search queries 500-2000 tokens typical
金額: Free; optional LLM providers cost normal LLM fees
ヒント: Use heuristic provider for first-pass compile; upgrade to LLM-backed compile only when quality matters.

セキュリティ

権限、シークレット、影響範囲

認証情報の保管： Optional LLM provider keys in env/config

データ送信先： None by default (heuristic); opt-in provider calls only

Vault content may include sensitive source material — .gitignore the vault dir by default.
Contradiction detection is heuristic; treat flags as 'investigate', not 'definitely wrong'.

トラブルシューティング

よくあるエラーと対処法

Compile fails on a specific PDF

Some PDFs are scanned/image-only. Pre-OCR with ocrmypdf before dropping in raw/.

確認： pdftotext file.pdf - | head

MCP connection fails after agent install

Re-run swarmvault install --agent <name> and restart the agent; config paths vary per platform.

確認： Client MCP list shows swarmvault

Hybrid search returns nothing

Vault not compiled yet, or embeddings not built for offline mode. Run swarmvault compile.

確認： swarmvault status

代替案

swarmvault 他との比較

代替案	代わりに使う場面	トレードオフ
documentation-server	You want quick drag-and-drop RAG without wiki compilation	No structured graph or contradiction detection
Obsidian + Smart Connections	You live in Obsidian and want in-editor AI	Less structured compile pipeline
NotebookLM	You're OK with Google-hosted, easy UI	Data leaves your machine; no graph export

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る