Downloads Confluence Cloud pages as Markdown with images, supporting space, single page, and page tree downloads, with multi-org support and customizable output directory.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Confluence Downloader Download the entire Engineering Wiki space"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Kiro Power and MCP server for downloading Confluence Cloud pages as Markdown with images.
Download entire spaces with folder hierarchy preserved
Download single pages or page trees (page + all descendants)
Images downloaded locally with markdown-compatible references
Multi-org support (override Confluence URL per request)
YAML frontmatter on each page (title, source URL, export timestamp)
Rate limiting, retry logic and exponential backoff
Related MCP server: md2confluence-mcp
In Kiro, open the Powers panel and use "Add Custom Power" → "Import from GitHub" with this repo URL.
After installing, configure your credentials in the Power's MCP settings:
Variable | Description |
| Default Atlassian site URL (can be overridden per request) |
| Your Atlassian login email |
| Unscoped API token |
Generate tokens at id.atlassian.com. The token must be unscoped; scoped tokens return 403 on the classic REST API.
pip install confluence-downloader-mcpOr run directly with uvx:
uvx confluence-downloader-mcpTool | Description |
| Verify credentials and list spaces |
| List all accessible spaces |
| Download all pages in a space |
| Download a single page by URL or ID |
| Download a page and all descendants |
Add to your MCP config (e.g. ~/.kiro/settings/mcp.json):
{
"mcpServers": {
"confluence-downloader": {
"command": "uvx",
"args": ["confluence-downloader-mcp"],
"env": {
"CONFLUENCE_URL": "https://your-site.atlassian.net",
"CONFLUENCE_EMAIL": "you@example.com",
"CONFLUENCE_API_TOKEN": "your-api-token"
}
}
}
}Files are saved to ./confluence-export/ in the current workspace by default. Pass output_dir to any download tool to save elsewhere.
MIT
This server cannot be deployed
Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
PDFs, JavaScript pages and ordinary HTML as clean Markdown. Follows robots.txt per RFC 9309.
Convert PDF, Word, PowerPoint, Excel, HTML and EPUB to Markdown, with OCR and RAG chunking
Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.
