/ 디렉터리 / 플레이그라운드 / mcp-logseq
● 커뮤니티 ergut ⚡ 바로 사용

mcp-logseq

제작: ergut · ergut/mcp-logseq

Make your Logseq graph AI-queryable — read pages, create blocks, search by property, run DSL queries — over Logseq's local HTTP API.

mcp-logseq by ergut connects an MCP client to Logseq's Local HTTP API. 16 core tools cover pages, blocks, namespaces, backlinks, and DSL queries. Optional vector search adds semantic recall across the whole graph.

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

logseq.replay ▶ 준비됨
0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "logseq": {
      "command": "uvx",
      "args": [
        "mcp-logseq"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "logseq": {
      "command": "uvx",
      "args": [
        "mcp-logseq"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "logseq": {
      "command": "uvx",
      "args": [
        "mcp-logseq"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "logseq": {
      "command": "uvx",
      "args": [
        "mcp-logseq"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "logseq",
      "command": "uvx",
      "args": [
        "mcp-logseq"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json
{
  "context_servers": {
    "logseq": {
      "command": {
        "path": "uvx",
        "args": [
          "mcp-logseq"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add logseq -- uvx mcp-logseq

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

사용 사례

실전 활용법: mcp-logseq

Draft today's daily journal from your week

👤 Logseq power users ⏱ ~10 min beginner

언제 쓸까: Friday reflection; you want a summary of the week's journal pages.

사전 조건
  • Logseq with HTTP API enabled — Settings > Features > enable HTTP APIs; generate API token
  • LOGSEQ_API_TOKEN + LOGSEQ_API_URL env vars — Set in your MCP client config
흐름
  1. Pull last week's journal pages
    Get the content of this week's daily journal pages (Monday through today).✓ 복사됨
    → Page contents per day
  2. Summarize and draft
    Summarize themes and draft today's journal with a Week Review section.✓ 복사됨
    → Draft ready to paste
  3. Write back
    Update today's journal page, appending the Week Review section.✓ 복사됨
    → Page updated

결과: A closing-the-loop weekly reflection with minimal typing.

함정
  • update_page in append mode duplicates content on retry — Use replace mode for idempotent operations, or check existing content first
  • Sensitive tags leak into summaries — Set LOGSEQ_EXCLUDE_TAGS=private,#secret to hide those

Find pages by property for a task sweep

👤 Logseq users with task-style pages ⏱ ~15 min beginner

언제 쓸까: You tag project pages with status:: active and want a list.

흐름
  1. Find by property
    find_pages_by_property: status=active. Return names and updated-at.✓ 복사됨
    → Page list
  2. Triage
    For each, fetch the page and tell me the last 3 blocks — is there a visible next action?✓ 복사됨
    → Per-page status

결과: A sweep of active projects with clear next actions.

Semantic recall across your whole graph

👤 Researchers with a huge Logseq graph ⏱ ~10 min intermediate

언제 쓸까: Keyword search isn't finding a note you know you wrote.

사전 조건
  • Vector DB synced — Run sync_vector_db once; re-run after big imports
흐름
  1. Vector search
    vector_search: 'what did I note about test pyramid vs honeycomb?'✓ 복사됨
    → Ranked matches
  2. Pull full page
    get_page_content on the top match.✓ 복사됨
    → Full content

결과: Finding notes by meaning, not exact words.

Turn a meeting page into tracked action items

👤 PMs and team leads ⏱ ~10 min beginner

언제 쓸까: You capture meetings in Logseq and want the actions separated.

흐름
  1. Read meeting page
    get_page_content for 'Meeting/2026-04-14/engineering-sync'.✓ 복사됨
    → Notes
  2. Extract actions
    Identify TODO-flavored lines. For each, create a child block under today's journal with assignee and due date.✓ 복사됨
    → Blocks created

결과: Actions lifted out of notes into a trackable list.

조합

다른 MCP와 조합해 10배 효율

logseq + marm-systems

Short-lived recall in MARM; durable notes in Logseq

Move these MARM contextual logs into Logseq as pages under /Notes/2026-04.✓ 복사됨
logseq + filesystem

Export curated Logseq pages to Markdown files

Export all pages tagged #public to ./exports/public-notes/ as individual .md files.✓ 복사됨

도구

이 MCP가 노출하는 것

도구입력언제 호출비용
list_pages (none) Graph overview free (local API)
get_page_content name: str Read a page free
create_page name, content, properties? New page free (write)
update_page name, content, mode: append|replace Edit an existing page free (write)
delete_page name: str Destructive — confirm free
search query: str Full-text search free
query dsl: str Logseq DSL query free
find_pages_by_property key: str, value?: str Filter by properties free
get_page_backlinks name: str Who links to this note free
insert_nested_block parent_uuid, content, position: child|sibling Add structured content free (write)
vector_search query: str Semantic recall free (local embeddings)

비용 및 제한

운영 비용

API 쿼터
None — Logseq's local API is unbounded
호출당 토큰
Small for list/search; pages can be long
금액
Free
For graphs with 10k+ pages, keep vector DB synced nightly rather than on every query.

보안

권한, 시크릿, 파급범위

자격 증명 저장: LOGSEQ_API_TOKEN in env var
데이터 외부 송신: All local to Logseq; vector embeddings stay on your machine
절대 부여 금지: Exposing Logseq's HTTP API to your LAN without firewalling

문제 해결

자주 발생하는 오류와 해결

Connection refused on localhost:12315

Start the HTTP API via the plug icon in Logseq. It's off by default.

확인: curl http://localhost:12315
401 on API calls

Token missing or mismatched. Regenerate in Logseq Authorization tokens.

확인: Check token in Logseq settings
vector_search empty

Run sync_vector_db first; it's not auto-synced.

확인: vector_db_status

대안

mcp-logseq 다른 것과 비교

대안언제 쓰나단점/장점
Obsidian MCP (community)You use Obsidian insteadDifferent graph semantics
Notion MCPYou're on NotionPaid SaaS; different graph model
filesystem MCP on the Logseq dirYou only need raw file accessNo block-level operations, no DSL queries

더 보기

리소스

📖 GitHub에서 공식 README 읽기

🐙 열린 이슈 보기

🔍 400+ MCP 서버 및 Skills 전체 보기