WikiJS MCP Server
Enables AI assistants to search, retrieve, and optionally edit pages in a WikiJS knowledge base via the Model Context Protocol.
README
WikiJS MCP Server
A Model Context Protocol (MCP) server that provides integration with WikiJS, allowing AI assistants to search and retrieve content from your WikiJS knowledge base.
Overview
This MCP server enables AI assistants to interact with WikiJS instances by providing tools to:
- Search for pages by query string
- Retrieve pages by ID
- Retrieve pages by path and locale
- Get all pages from the wiki
- Edit pages (when enabled)
Installation
Using npx (recommended)
npx @cahaseler/wikijs-mcp
The binary will be available as wikijs-mcp-edit to avoid conflicts with the original package.
From source
git clone https://github.com/cahaseler/wikijs-mcp.git
cd wikijs-mcp
npm install
npm run build
Configuration
Claude Code
Method 1: Using the CLI (Recommended)
# Add as a user-scoped server (available across all projects)
claude mcp add wikijs \
-e WIKIJS_URL=https://your-wiki.example.com \
-e WIKIJS_API_KEY=your-api-key \
-- npx @cahaseler/wikijs-mcp
# Or with edit functionality enabled
claude mcp add wikijs \
-e WIKIJS_URL=https://your-wiki.example.com \
-e WIKIJS_API_KEY=your-api-key \
-e WIKIJS_ENABLE_EDIT=true \
-- npx @cahaseler/wikijs-mcp
Method 2: Project-scoped configuration
Create a .mcp.json file in your project root:
{
"mcpServers": {
"wikijs": {
"command": "npx",
"args": ["@cahaseler/wikijs-mcp"],
"env": {
"WIKIJS_URL": "https://your-wiki.example.com",
"WIKIJS_API_KEY": "your-api-key",
"WIKIJS_ENABLE_EDIT": "false"
}
}
}
}
Cursor
Add to your Cursor settings (.cursor/settings.json):
{
"mcpServers": {
"wikijs-mcp": {
"command": "npx",
"args": ["@cahaseler/wikijs-mcp"],
"env": {
"WIKIJS_URL": "https://your-wiki.example.com",
"WIKIJS_API_KEY": "your-api-key",
"WIKIJS_ENABLE_EDIT": "false"
}
}
}
}
Claude Desktop
Add to your Claude Desktop configuration:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"wikijs-mcp": {
"command": "npx",
"args": ["@cahaseler/wikijs-mcp"],
"env": {
"WIKIJS_URL": "https://your-wiki.example.com",
"WIKIJS_API_KEY": "your-api-key",
"WIKIJS_ENABLE_EDIT": "false"
}
}
}
}
Getting a WikiJS API Key
- Log into your WikiJS instance as an administrator
- Go to Administration > API Access
- Enable the API if not already enabled
- Click New API Key
- Give it a name (e.g., "MCP Server")
- Select Full Access or configure specific permissions
- Set an appropriate expiration date
- Copy the generated key immediately (it won't be shown again)
Environment Variables
| Variable | Description | Required | Default |
|---|---|---|---|
WIKIJS_URL |
URL of your WikiJS instance | Yes | - |
WIKIJS_API_KEY |
WikiJS API key | Yes | - |
WIKIJS_ENABLE_EDIT |
Enable page editing functionality | No | false |
Available Tools
Once configured, the following tools will be available:
-
search_pages - Search for pages by query string
- Parameters:
query(required),path(optional),locale(optional)
- Parameters:
-
get_page_by_id - Retrieve a specific page by its ID
- Parameters:
id(required)
- Parameters:
-
get_page_by_path - Retrieve a page by its path and locale
- Parameters:
path(required),locale(required)
- Parameters:
-
get_all_pages - List all pages with optional filters
- Parameters:
limit(optional),locale(optional),tags(optional)
- Parameters:
-
create_page - Create a new WikiJS page (only when
WIKIJS_ENABLE_EDIT=true)- Parameters:
title(required),content(required),description(required),path(required),editor(optional),isPublished(optional),isPrivate(optional),locale(optional),tags(optional)
- Parameters:
-
edit_page - Edit a WikiJS page (only when
WIKIJS_ENABLE_EDIT=true)- Parameters:
id(required),title,content,description,editor,isPublished,isPrivate,locale,tags,path
- Parameters:
Development
Prerequisites
- Node.js 18+
- Docker (for local WikiJS testing)
- npm or yarn
Setup
- Clone the repository:
git clone https://github.com/cahaseler/wikijs-mcp.git
cd wikijs-mcp
- Install dependencies:
npm install
- Copy the environment template:
cp env.example .env
- Edit
.envwith your WikiJS credentials
Local WikiJS Instance
To run a local WikiJS instance for testing:
# Start WikiJS and PostgreSQL
docker-compose up -d
# The instance will be available at http://localhost:3000
# Follow the setup wizard to create an admin account
Building
# Using npm
npm run build
# Using make
make build
Testing the MCP Server
# Run the built server
node build/index.js
# Or use the make command
make run
Security Considerations
- API Key Storage: Never commit your API key to version control
- Edit Permissions: The edit functionality is disabled by default. Only enable it if you trust the environment where the MCP server is running
- Scope Permissions: When creating the WikiJS API key, consider using the minimum required permissions instead of full access
Troubleshooting
"WIKIJS_URL and WIKIJS_API_KEY must be set"
Ensure your environment variables are properly configured. Check your .env file or the environment variables in your MCP client configuration.
"Failed to update page: Unauthorized"
Your API key may be expired or lack the necessary permissions. Create a new API key with appropriate permissions.
GraphQL errors during development
If you modify the GraphQL queries, regenerate the types:
npm run codegen
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
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。