swarmvault MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

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>

Живое демо

Как выглядит на практике

swarmvault.replay ▶ готово

0/0

Установка

Выберите клиент

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

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

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

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

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

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

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

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

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add swarmvault -- npx -y swarmvault

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: swarmvault

Compound research across months into a queryable wiki

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

Когда использовать: You've been researching a topic for weeks and realize your notes are scattered.

Предварительные требования

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

Поток

Dump raw sources

Drop everything into raw/: PDFs, saved articles, meeting transcripts, code snippets.✓ Скопировано

→ Immutable raw/ folder populated
Compile the wiki

swarmvault compile — generate wiki/ with typed pages and link frontmatter.✓ Скопировано

→ Wiki pages created
Query through MCP

Via the MCP: what's the current consensus in my notes about 'post-quantum TLS timeline'? Include contradictions.✓ Скопировано

→ Answer with graph-walked citations and flagged contradictions

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

Подводные камни

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

Сочетать с: documentation-server

Turn meeting transcripts into structured team knowledge

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

Когда использовать: You have Fathom/Otter transcripts piling up and want to query across them.

Поток

Drop transcripts in raw/

Copy all my Otter transcripts from last quarter into raw/meetings/.✓ Скопировано

→ Files in place
Compile

swarmvault compile. Confirm entities (people, projects) were extracted.✓ Скопировано

→ Entity count report
Query

What did we decide about the pricing overhaul across all Q1 meetings? Cite each source.✓ Скопировано

→ Consolidated answer with source transcripts cited

Итог: Institutional memory that survives people leaving.

Build a book-club wiki with cross-book reasoning

👤 Serious readers ⏱ ~90 min intermediate

Когда использовать: You want the AI to reason across books, not just one at a time.

Поток

Ingest

Drop PDFs + notes for 5 books into raw/; compile.✓ Скопировано

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

Which concepts show up in 3+ books? Identify contradictions between authors.✓ Скопировано

→ Concept map with contradictions flagged

Итог: A reading practice that compounds.

Комбинации

Сочетайте с другими MCP — эффект x10

swarmvault + documentation-server

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

Ingest new papers into both — compare retrieval quality and structure.✓ Скопировано

swarmvault + logseq

Export vault pages into a Logseq graph

Export wiki/ Markdown into my Logseq pages/ dir with frontmatter preserved.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
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

Стоимость и лимиты

Во что обходится

Квота API: Zero with the heuristic provider; otherwise your LLM provider's limits
Токенов на вызов: Compile can stream large source content through embeddings; search queries 500-2000 tokens typical
Деньги: Free; optional LLM providers cost normal LLM fees
Совет: Use heuristic provider for first-pass compile; upgrade to LLM-backed compile only when quality matters.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: Optional LLM provider keys in env/config

Исходящий трафик: 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'.

Устранение неполадок

Частые ошибки и исправления

Compile fails on a specific PDF

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

Проверить: 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.

Проверить: Client MCP list shows swarmvault

Hybrid search returns nothing

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

Проверить: swarmvault status

Альтернативы

swarmvault в сравнении

Альтернатива	Когда использовать	Компромисс
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

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills