swarmvault MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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>

Live-Demo

In der Praxis

swarmvault.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

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

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

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

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

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

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

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

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

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add swarmvault -- npx -y swarmvault

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: swarmvault

Compound research across months into a queryable wiki

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

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

Voraussetzungen

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

Ablauf

Dump raw sources

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

→ Immutable raw/ folder populated
Compile the wiki

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

→ Wiki pages created
Query through MCP

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

→ Answer with graph-walked citations and flagged contradictions

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

Fallstricke

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

Kombinieren mit: documentation-server

Turn meeting transcripts into structured team knowledge

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

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

Ablauf

Drop transcripts in raw/

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

→ Files in place
Compile

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

→ Entity count report
Query

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

→ Consolidated answer with source transcripts cited

Ergebnis: Institutional memory that survives people leaving.

Build a book-club wiki with cross-book reasoning

👤 Serious readers ⏱ ~90 min intermediate

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

Ablauf

Ingest

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

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

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

→ Concept map with contradictions flagged

Ergebnis: A reading practice that compounds.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

swarmvault + documentation-server

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

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

swarmvault + logseq

Export vault pages into a Logseq graph

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

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
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

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Zero with the heuristic provider; otherwise your LLM provider's limits
Tokens pro Aufruf: Compile can stream large source content through embeddings; search queries 500-2000 tokens typical
Kosten in €: Free; optional LLM providers cost normal LLM fees
Tipp: Use heuristic provider for first-pass compile; upgrade to LLM-backed compile only when quality matters.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Optional LLM provider keys in env/config

Datenabfluss: 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'.

Fehlerbehebung

Häufige Fehler und Lösungen

Compile fails on a specific PDF

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

Prüfen: 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.

Prüfen: Client MCP list shows swarmvault

Hybrid search returns nothing

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

Prüfen: swarmvault status

Alternativen

swarmvault vs. andere

Alternative	Wann stattdessen	Kompromiss
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

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen