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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.