confluence-markdown
MCP server for bidirectional Markdown-to-Confluence sync, enabling download and publish of Confluence pages as Markdown with images, frontmatter tracking, and dry-run safety.
README
Confluence Markdown
Bidirectional Markdown-to-Confluence sync. Download pages as Markdown, publish and update them back with images and mermaid diagrams.
Features
- Download spaces, pages and page trees as Markdown with images
- Publish new Confluence pages from local Markdown files
- Update existing pages with version conflict detection
- Publish directory trees as page hierarchies
- Mermaid diagrams rendered to PNG and uploaded as attachments
- Local image upload as page attachments
- Dry-run by default for all write operations
- Multi-org support (override Confluence URL per request)
- YAML frontmatter for page tracking (ID, version, space)
- Full-width page layout applied automatically
- Homepage support (update space homepage from a markdown file)
Setup
- Clone this repo
- Install dependencies:
pip install -e .
- Create a
.envfile in the project root:
CONFLUENCE_URL=https://your-site.atlassian.net
CONFLUENCE_EMAIL=you@example.com
CONFLUENCE_API_TOKEN=your-api-token
Generate tokens at id.atlassian.com. Token must be unscoped.
Project Config
Each project that publishes to Confluence needs a confluence.json:
{
"space_key": "ECM",
"confluence_url": "https://rebura.atlassian.net",
"docs_dir": "Design Documents",
"parent_page_id": "1915061323"
}
Usage
Sync a project (dry-run)
python -c "import sys; sys.path.insert(0, r'<path-to-this-repo>'); from confluence_markdown_mcp import sync_project; print(sync_project(r'<path-to-confluence.json>'))"
Sync a project (execute)
python -c "import sys; sys.path.insert(0, r'<path-to-this-repo>'); from confluence_markdown_mcp import sync_project; print(sync_project(r'<path-to-confluence.json>', confirm=True))"
Update a single page
python -c "import sys; sys.path.insert(0, r'<path-to-this-repo>'); from confluence_markdown_mcp import update_page; print(update_page(r'<path-to-file.md>', confirm=True))"
Publish a single new page
python -c "import sys; sys.path.insert(0, r'<path-to-this-repo>'); from confluence_markdown_mcp import publish_page; print(publish_page(r'<path-to-file.md>', confirm=True))"
Kiro Integration
A steering file is included at .kiro/steering/confluence-sync.md. Reference it with #confluence-sync in Kiro chat to enable conversational sync (e.g. "upload to confluence").
Frontmatter
Files track their Confluence state via YAML frontmatter:
---
title: "Page Title"
confluence_page_id: "123456"
confluence_space_key: "ECM"
confluence_version: 3
confluence_homepage: true
---
confluence_homepage: true- updates the space's existing homepage content instead of creating a new page- Files without
confluence_page_idare created as new pages - Files with
confluence_page_idare updated in place
Mermaid Diagrams
Mermaid code blocks are automatically rendered to PNG (2x scale, white background) and uploaded as page attachments. The source mermaid stays in your local files.
Requires mmdc (Mermaid CLI): npm install -g @mermaid-js/mermaid-cli
License
MIT
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。