Confluence Reader MCP Server
Allows reading Confluence Cloud pages as markdown, browsing page trees, downloading image attachments, and diffing content against local documentation.
Click on "Install 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 Reader MCP Serverfetch the Confluence page at https://example.atlassian.net/wiki/spaces/DEV/pages/123456"
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.
Confluence Reader MCP Server
An MCP server that lets AI assistants read Confluence Cloud pages as markdown, browse page trees, download image attachments, and diff content against local documentation.
Features
Fetch a single Confluence page as proper GitHub-flavored markdown (headings, tables, lists, code blocks)
List child pages for recursive traversal
Download image attachments by filename
Compare local content against a Confluence page with a unified diff
Supports scoped API tokens with Basic Auth
Related MCP server: MCP Atlassian Server
Setup
1. Get a Confluence API Token
Create a scoped API token from your Atlassian account: https://support.atlassian.com/confluence/kb/scoped-api-tokens-in-confluence-cloud/
2. Set Environment Variables
Add to your shell profile (~/.zshrc, ~/.bashrc, etc.):
export CONFLUENCE_TOKEN="your_scoped_token"
export CONFLUENCE_EMAIL="your_email@example.com"
export CONFLUENCE_CLOUD_ID="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"Reload your shell or open a new terminal.
Variable | Required | Description |
| Yes | Scoped API token |
| Yes | Email tied to your Atlassian account |
| Yes* | Cloud ID — routes via |
| Yes* | Direct tenant URL, e.g. |
*One of CONFLUENCE_CLOUD_ID or CONFLUENCE_BASE_URL is required. CONFLUENCE_CLOUD_ID is recommended.
3. Add to MCP Config
{
"mcpServers": {
"confluence-reader": {
"command": "npx",
"args": ["@satiyap/confluence-reader-mcp"]
}
}
}Restart the MCP host to pick up the new server.
Tools
confluence.fetch_page
Fetches a single Confluence page by URL and returns its content as markdown. Lists any direct child pages at the bottom so the caller can decide which to fetch next.
Parameter | Type | Description |
| string | Confluence page URL |
confluence.list_children
Lists the direct child pages of a Confluence page without fetching their content. Useful for discovering page structure before fetching individual pages.
Parameter | Type | Description |
| string | Confluence page URL |
confluence.fetch_image
Downloads an image attachment from a Confluence page by filename and saves it to a local directory.
Parameter | Type | Description |
| string | Confluence page URL |
| string | Attachment filename (e.g. |
| string | Local directory path to save the image to |
confluence.compare
Generates a git-style unified diff between a Confluence page and a local markdown string.
Parameter | Type | Description |
| string | Confluence page URL |
| string | Local markdown to compare against |
Returns a JSON object with additions, deletions, totalChanges, and the full diff.
Supported URL Formats
/wiki/spaces/SPACEKEY/pages/123456789/Page+Title/wiki/pages/viewpage.action?pageId=123456789
Security
Credentials are read from environment variables only — never passed in config files.
Use scoped tokens with the minimum permissions needed.
Contributing
Contributions are welcome. Please open an issue or submit a pull request.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/satiyap/confluence-reader-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server