WikiJS MCP Server
A Model Context Protocol server that enables Claude to read and update documentation in Wiki.js instances through capabilities like searching, reading, creating, and updating wiki pages.
README
WikiJS MCP Server
A Model Context Protocol (MCP) server for integrating with Wiki.js instances, enabling Claude to read and update documentation.
Features
- Search Pages: Find pages by title or content
- Read Pages: Get full page content by path or ID
- List Pages: Browse all pages with pagination
- Page Tree: View wiki structure as a tree
- Create Pages: Add new documentation pages
- Update Pages: Modify existing page content
- Authentication: Secure API key-based access
Installation
- Clone this repository:
git clone <repository-url>
cd wikijs-mcp
- Install dependencies:
pip install -e .
- Configure environment:
cp .env.example .env
# Edit .env with your Wiki.js details
Configuration
Create a .env file with your Wiki.js configuration:
WIKIJS_URL=https://your-wiki.example.com
WIKIJS_API_KEY=your_api_key_here
WIKIJS_GRAPHQL_ENDPOINT=/graphql # Optional, defaults to /graphql
DEBUG=false # Optional, enables debug logging
Getting Wiki.js API Key
- Log into your Wiki.js admin panel
- Go to Administration → API Access
- Enable the API if not already enabled
- Click New API Key
- Set appropriate permissions for your use case
- Add the key to your
.envfile
Usage
🐳 Docker (Recommended)
Quick Start with Docker
-
Create your
.envfile in the project root with your WikiJS settings -
Start the server:
docker compose up -d wikijs-mcp-server
- View logs:
docker compose logs -f wikijs-mcp-server
Docker Management Commands
# Start server in background
docker compose up -d wikijs-mcp-server
# Access interactive shell
docker compose run --rm wikijs-mcp-server bash
# Stop server
docker compose down
Docker with Claude Code
Add to your Claude Code MCP configuration:
{
"mcpServers": {
"wikijs": {
"command": "docker",
"args": ["exec", "-i", "wikijs-mcp-server", "python3", "-m", "wikijs_mcp.server"],
"env": {
"DOCKER_CONTAINER": "wikijs-mcp-server"
}
}
}
}
Standalone Server
Run the server directly:
python -m wikijs_mcp.server
With Claude Code (Native)
Add to your Claude Code MCP configuration:
{
"mcpServers": {
"wikijs": {
"command": "python3",
"args": ["-m", "wikijs_mcp.server"],
"cwd": "/path/to/wikijs-mcp"
}
}
}
Available Tools
wiki_search
Search for pages by title or content.
- Parameters:
query(string),limit(optional integer)
wiki_get_page
Get a specific page by path or ID.
- Parameters:
path(string) ORid(integer)
wiki_list_pages
List all pages.
- Parameters:
limit(optional integer)
wiki_get_tree
Get wiki page tree structure.
- Parameters:
parent_path(optional string)
wiki_create_page
Create a new wiki page.
- Parameters:
path(string),title(string),content(string),description(optional),tags(optional array)
wiki_update_page
Update an existing wiki page.
- Parameters:
id(integer),content(string),title(optional),description(optional),tags(optional array)
Example Usage with Claude
# Search for documentation
"Search for pages about authentication"
# Read a specific page
"Get the content of the page at path 'docs/api/authentication'"
# Update documentation
"Update page ID 123 with improved authentication examples"
# Create new documentation
"Create a new page at 'docs/troubleshooting/common-issues' with troubleshooting guide"
Development
Setup Development Environment
Install development dependencies:
pip install -e ".[dev]"
Testing
The project has comprehensive test coverage with pytest:
# Run all tests
pytest
# Run with coverage report
pytest --cov=wikijs_mcp --cov-report=html
# Run specific test categories
pytest -m unit # Unit tests only
pytest -m integration # Integration tests only
# Run tests in parallel (faster)
pytest -n auto
Test Categories
- Unit tests (
-m unit): Fast, isolated component tests - Integration tests (
-m integration): Full MCP server functionality tests - Network tests (
-m network): Tests requiring network access (skipped by default)
Code Quality
Format code:
black wikijs_mcp/ tests/
Type checking:
mypy wikijs_mcp/
Security scanning:
bandit -r wikijs_mcp/
safety check
Docker Testing
Test the Docker build:
docker compose build
docker compose run --rm wikijs-mcp-server bash
CI/CD
The project uses GitHub Actions for:
- ✅ Multi-Python testing (3.8-3.12)
- ✅ Code quality checks (black, mypy)
- ✅ Security scanning (bandit, safety)
- ✅ Docker build testing
- ✅ Coverage reporting (Codecov)
Requirements
- Python 3.8+
- Wiki.js 2.2+ (for API access)
- Valid Wiki.js API key with appropriate permissions
License
MIT 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。