Slite MCP Server
A Model Context Protocol server for Slite, enabling AI assistants to interact with your Slite knowledge base through note management, search, and AI queries.
README
@takeokunn/slite-mcp
A Model Context Protocol (MCP) server for Slite, enabling AI assistants to interact with your Slite knowledge base.
Features
- Note Management - Create, read, update, delete, archive, and verify notes
- Search - Full-text search across all Slite notes with advanced filtering
- Ask AI - Query notes using natural language with Slite's AI
- User Management - Look up users by ID or search by name/email
- Group Management - Look up groups by ID or search by name
- Tile Management - Update or create structured tiles within notes
- Secure Bearer Token Authentication - API token-based access control
- TypeScript Implementation - Full type safety throughout
Installation
npm install -g @takeokunn/slite-mcp
Or run directly with npx:
npx @takeokunn/slite-mcp
Configuration
Set the following environment variable:
| Variable | Description | Example |
|---|---|---|
SLITE_API_TOKEN |
Slite API token | your_slite_api_token |
Getting an API Token
- Log in to Slite
- Go to Settings → Integrations → API
- Generate a new API token
- Copy the generated token
Usage
Claude Desktop Integration
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"slite": {
"command": "npx",
"args": ["@takeokunn/slite-mcp"],
"env": {
"SLITE_API_TOKEN": "your_slite_api_token"
}
}
}
}
Or if installed globally:
{
"mcpServers": {
"slite": {
"command": "slite-mcp",
"env": {
"SLITE_API_TOKEN": "your_slite_api_token"
}
}
}
}
Available Tools
This MCP server provides 21 tools organized into 7 categories:
Ask Tools (4)
| Tool | Description |
|---|---|
ask_question |
Ask a natural language question about your Slite notes |
index_custom_content |
Index custom content for AskX (deprecated) |
delete_custom_content |
Delete indexed custom content (deprecated) |
list_custom_content |
List indexed custom content (deprecated) |
Me Tools (1)
| Tool | Description |
|---|---|
get_me |
Get the currently authenticated user information |
Note Tools (10)
| Tool | Description |
|---|---|
create_note |
Create a new note from markdown or HTML content |
list_notes |
List notes with optional filtering by owner or parent |
get_note |
Get a single note by ID with content |
delete_note |
Delete a note and all its children (irreversible) |
update_note |
Update a note's title or content |
get_note_children |
Get child notes of a parent note |
verify_note |
Mark a note as verified with optional expiration |
flag_note_as_outdated |
Flag a note as outdated with a reason |
archive_note |
Archive or unarchive a note |
update_note_owner |
Change the owner of a note to a user or group |
Tile Tools (1)
| Tool | Description |
|---|---|
update_tile |
Update or create a tile in a Slite note |
Search Tools (1)
| Tool | Description |
|---|---|
search_notes |
Search notes by query with filters for review state, date, and more |
User Tools (2)
| Tool | Description |
|---|---|
get_user |
Get a single user by ID |
search_users |
Search users by email, name, or username |
Group Tools (2)
| Tool | Description |
|---|---|
get_group |
Get a single group by ID |
search_groups |
Search groups by name |
Requirements
- Node.js 22+
- Slite account with API access
License
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。