swarmvault MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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>

Démo en direct

Aperçu en pratique

swarmvault.replay ▶ prêt

0/0

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add swarmvault -- npx -y swarmvault

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : swarmvault

Compound research across months into a queryable wiki

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

Quand l'utiliser : You've been researching a topic for weeks and realize your notes are scattered.

Prérequis

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

Déroulement

Dump raw sources

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

→ Immutable raw/ folder populated
Compile the wiki

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

→ Wiki pages created
Query through MCP

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

→ Answer with graph-walked citations and flagged contradictions

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

Pièges

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

Combiner avec : documentation-server

Turn meeting transcripts into structured team knowledge

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

Quand l'utiliser : You have Fathom/Otter transcripts piling up and want to query across them.

Déroulement

Drop transcripts in raw/

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

→ Files in place
Compile

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

→ Entity count report
Query

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

→ Consolidated answer with source transcripts cited

Résultat : Institutional memory that survives people leaving.

Build a book-club wiki with cross-book reasoning

👤 Serious readers ⏱ ~90 min intermediate

Quand l'utiliser : You want the AI to reason across books, not just one at a time.

Déroulement

Ingest

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

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

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

→ Concept map with contradictions flagged

Résultat : A reading practice that compounds.

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

swarmvault + documentation-server

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

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

swarmvault + logseq

Export vault pages into a Logseq graph

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: Zero with the heuristic provider; otherwise your LLM provider's limits
Tokens par appel: Compile can stream large source content through embeddings; search queries 500-2000 tokens typical
Monétaire: Free; optional LLM providers cost normal LLM fees
Astuce: Use heuristic provider for first-pass compile; upgrade to LLM-backed compile only when quality matters.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : Optional LLM provider keys in env/config

Sortie de données : 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'.

Dépannage

Erreurs courantes et correctifs

Compile fails on a specific PDF

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

Vérifier : 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.

Vérifier : Client MCP list shows swarmvault

Hybrid search returns nothing

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

Vérifier : swarmvault status

Alternatives

swarmvault vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills