swarmvault MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

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>

라이브 데모

실제 사용 모습

swarmvault.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

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

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

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

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

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

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add swarmvault -- npx -y swarmvault

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: swarmvault

Compound research across months into a queryable wiki

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

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

사전 조건

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

흐름

Dump raw sources

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

→ Immutable raw/ folder populated
Compile the wiki

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

→ Wiki pages created
Query through MCP

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

→ Answer with graph-walked citations and flagged contradictions

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

함정

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

함께 쓰기: documentation-server

Turn meeting transcripts into structured team knowledge

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

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

흐름

Drop transcripts in raw/

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

→ Files in place
Compile

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

→ Entity count report
Query

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

→ Consolidated answer with source transcripts cited

결과: Institutional memory that survives people leaving.

Build a book-club wiki with cross-book reasoning

👤 Serious readers ⏱ ~90 min intermediate

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

흐름

Ingest

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

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

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

→ Concept map with contradictions flagged

결과: A reading practice that compounds.

조합

다른 MCP와 조합해 10배 효율

swarmvault + documentation-server

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

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

swarmvault + logseq

Export vault pages into a Logseq graph

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

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

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

보안

권한, 시크릿, 파급범위

자격 증명 저장: Optional LLM provider keys in env/config

데이터 외부 송신: 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'.

문제 해결

자주 발생하는 오류와 해결

Compile fails on a specific PDF

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

확인: 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.

확인: Client MCP list shows swarmvault

Hybrid search returns nothing

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

확인: swarmvault status

대안

swarmvault 다른 것과 비교

대안	언제 쓰나	단점/장점
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

swarmvault