Logseq MCP Server
Connects AI assistants to Logseq knowledge graphs to read, write, and search pages, blocks, and journals via the Model Context Protocol. It features 17 tools for full graph management, including CRUD operations, batch block insertion, and full-text search.
README
logseq-mcp-server
A TypeScript Model Context Protocol (MCP) server that connects AI assistants to your Logseq knowledge graph. Read, write, search, and manage pages, blocks, journals, and tags through the MCP protocol.
Features
- 17 tools covering Pages, Blocks, Search, Journals, and Graph operations
- Full CRUD for pages and blocks
- Full-text search across the graph
- Batch block insertion with nested children
- Block property management
- Backlink (linked references) retrieval
- Journal page creation and tag listing
- Dual transport: stdio (local) and HTTP (Hono-based, portable across runtimes)
Prerequisites
- Logseq installed and running
- HTTP APIs server enabled in Logseq:
- Settings > Features > Enable "HTTP APIs server"
- Click the API button > "Start server"
- Generate a token: API panel > Authorization tokens
- Node.js >= 18
Quick Start
Claude Desktop
Add to Settings > Developer > Edit Config:
{
"mcpServers": {
"logseq": {
"command": "npx",
"args": ["logseq-mcp-server"],
"env": {
"LOGSEQ_API_TOKEN": "your_token_here"
}
}
}
}
Claude Code
claude mcp add logseq-mcp-server \
--env LOGSEQ_API_TOKEN=your_token_here \
-- npx logseq-mcp-server
From Source
git clone https://github.com/user/logseq-mcp-server.git
cd logseq-mcp-server
npm install
npm run build
LOGSEQ_API_TOKEN=your_token npm start
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
LOGSEQ_API_TOKEN |
Yes | - | Bearer token from Logseq HTTP API |
LOGSEQ_API_URL |
No | http://127.0.0.1:12315 |
Logseq HTTP API URL |
TRANSPORT |
No | stdio |
Transport mode: stdio or http |
PORT |
No | 3000 |
HTTP port (when TRANSPORT=http) |
HTTP Transport
When running with TRANSPORT=http, the server uses Hono with WebStandardStreamableHTTPServerTransport from the MCP SDK.
LOGSEQ_API_TOKEN=your_token TRANSPORT=http PORT=3000 npm start
Endpoints:
POST|GET|DELETE /mcp- MCP Streamable HTTP protocolGET /health- Health check
curl http://localhost:3000/health
# {"status":"ok","server":"logseq-mcp-server"}
Available Tools
Pages
| Tool | Description |
|---|---|
logseq_list_pages |
List pages with filtering (journal, namespace) and pagination |
logseq_get_page |
Get page metadata by name or UUID |
logseq_get_page_content |
Get full block tree rendered as indented Markdown |
logseq_create_page |
Create a new page with optional initial content and properties |
logseq_delete_page |
Permanently delete a page |
logseq_rename_page |
Rename a page (updates all references) |
logseq_get_page_linked_references |
Get backlinks - pages and blocks that reference a page |
Blocks
| Tool | Description |
|---|---|
logseq_get_block |
Get a block by UUID with optional children |
logseq_insert_block |
Insert a block relative to a page or block |
logseq_append_block |
Append a block at the end of a page |
logseq_update_block |
Update block content and properties |
logseq_remove_block |
Permanently remove a block |
logseq_move_block |
Move a block to a new position |
logseq_insert_batch_blocks |
Insert multiple blocks at once (supports nesting) |
logseq_block_property |
Read or write a single block property |
Search & Graph
| Tool | Description |
|---|---|
logseq_search |
Full-text search across pages and blocks |
logseq_create_journal |
Create a journal page for a specific date |
logseq_get_graph_info |
Get current graph name and path |
logseq_get_all_tags |
List all tags in the graph |
Architecture
src/
├── index.ts # Entry point, server init, transport selection
├── constants.ts # Shared constants
├── types.ts # TypeScript type definitions
├── schemas/
│ └── index.ts # Zod input validation schemas
├── services/
│ ├── logseq-client.ts # Logseq HTTP API client
│ └── formatters.ts # Response formatting helpers
└── tools/
├── page-tools.ts # Page CRUD tools
├── block-tools.ts # Block CRUD tools
└── search-graph-tools.ts # Search, journal, graph tools
MCP Client (Claude, etc.)
↓ stdio or HTTP
MCP Server (index.ts, Hono)
↓ registers tool groups
Tools (page-tools, block-tools, search-graph-tools)
↓ calls service methods
LogseqClient (logseq-client.ts)
↓ POST /api { method, args }
Logseq HTTP API (local instance)
Development
npm install # Install dependencies
npm run build # Compile TypeScript
npm run dev # Watch mode (tsc --watch)
npm run inspect # Test with MCP Inspector
License
Apache-2.0
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。