Confluence Cloud MCP Server
Provides tools for managing Confluence Cloud pages, spaces, content editing with session-based change tracking, native macro support, search, media attachments, and graph-based navigation via Confluence Cloud API.
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 Cloud MCP Server get the content of page 'Product Roadmap 2025'"
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 Cloud MCP Server
A Model Context Protocol server for interacting with Confluence Cloud. Structured page editing with session-based change tracking, native macro support, and graph-based navigation.
Install
Claude Desktop (one-click)
Download confluence-cloud-mcp.mcpb and open it — Claude Desktop will prompt for your Confluence credentials.
Claude Code
claude mcp add confluence-cloud -e CONFLUENCE_API_TOKEN=your-token -e CONFLUENCE_EMAIL=your-email -e CONFLUENCE_HOST=https://your-team.atlassian.net -- npx -y @aaronsb/confluence-cloud-mcpManual (any MCP client)
{
"mcpServers": {
"confluence-cloud": {
"command": "npx",
"args": ["-y", "@aaronsb/confluence-cloud-mcp"],
"env": {
"CONFLUENCE_API_TOKEN": "your-api-token",
"CONFLUENCE_EMAIL": "your-email",
"CONFLUENCE_HOST": "https://your-team.atlassian.net"
}
}
}
}Credentials
Generate an API token at Atlassian Account Settings.
Related MCP server: MCP Atlassian Server
Tools
Tool | Description |
| Get, create, update, delete, move, copy, or pull pages for editing |
| Structural block editing within a tracked session — patch sections, append, replace, find/replace, sync |
| List spaces, get space details, or manage space configuration |
| Search using CQL, full-text, labels, or contributors |
| Upload, download, list, or delete page attachments |
| Traverse page hierarchy, discover backlinks (via GraphQL), forward links, and related pages |
| Batch multiple operations with result references ( |
Each tool accepts an operation parameter (except queue_confluence_operations which takes an operations array). Per-tool documentation is available as MCP resources at confluence://tools/{tool_name}/documentation.
Key Features
Session-based editing — Pull a page into a tracked session, make surgical edits to individual blocks (sections, paragraphs, macros, tables), then sync only what changed. No full-page rewrites.
Native macro support — Status badges, info/warning/error panels, expand blocks, and table of contents render as readable :::directive syntax. The server handles ADF serialization with correct native node types.
GraphQL navigation — Backlinks and forward links use the Atlassian GraphQL gateway's link graph for accurate, fast relationship discovery. Falls back to REST when GraphQL is unavailable.
Rendering facades — Every response is token-efficient markdown with context-aware next-step hints. No raw JSON.
MCP Resources
Resource | Description |
| Available macro registry with parameter schemas and usage examples |
Architecture
See docs/architecture/INDEX.md for the 8 ADRs covering the five-layer architecture, hybrid client, content model, session editing, macro handling, navigation, and rendering facades.
License
Available Tools
8 toolsedit_confluence_contentB
Line-addressed content editing within a scratchpad buffer. View, insert, replace, or remove lines, then submit to Confluence. Requires a scratchpadId from create or pull_for_editing.
Inputs: operation (required), content, endLine, message, +3 more.
manage_confluence_mediaB
Upload, download, list, view, or delete page attachments and media. Use view to display images inline.
Inputs: operation (required), pageId, content, filename, +3 more.
manage_confluence_pageC
Get, create, update, delete, move, copy, archive, or pull pages for editing. Read and add comments. Manage labels and content properties. Create returns a scratchpad for composing content before publishing. Use pull_for_editing to load existing page content into a scratchpad. Archive/unarchive pages or entire page trees.
Inputs: operation (required), body, label, title, +9 more.
manage_confluence_spaceC
List spaces, get space details, or manage space configuration.
Inputs: operation (required), name, limit, cursor, +2 more.
manage_workspaceA
Stage files in the local workspace for attachment operations. List, read, write, delete files, or create directories. Supports nested paths (e.g. "projects/images/photo.png"). Downloaded attachments land here; upload can read from here. All responses include the absolute filesystem path.
Inputs: operation (required), content, filename, destination.
queue_confluence_operationsA
Batch multiple Confluence operations in a single call. Supports result references ($0.pageId) and per-operation error strategies.
Inputs: operations (required).
search_confluenceA
Search Confluence using CQL (Confluence Query Language), full-text search, or filter by labels/contributors.
Inputs: operation (required), cql, limit, query, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Most tools are clearly distinct, but manage_confluence_page and edit_confluence_content both involve editing page content. The descriptions clarify that edit_confluence_content operates on scratchpad buffers only, so agents can differentiate, though the boundary could confuse.
All tools follow a consistent verb_noun snake_case pattern (e.g., manage_confluence_page, search_confluence). Even the slightly different navigate_confluence and queue_confluence_operations fit the verb-based style without breaking the pattern.
8 tools is well within the ideal range for a domain server. Each tool covers a meaningful area—pages, media, workspace, navigation, batching, search, content editing, and spaces—without unnecessary fragmentation.
The surface covers core Confluence workflows: page lifecycle, media, spaces, search, navigation, and batching. Minor gaps exist such as explicit permission/user management, but the included operations handle most common needs and comments are coverable through the page tool.
Maintenance
Related MCP Connectors
Connect to Atlassian Jira, Confluence, Loom, and more to search, create, and manage your work.
Query, explore, and manage your databases through natural conversation.
Streamline your Attio workflows using natural language to search, create, update, and organize com…
Get content approved & published faster: draft, send approval links and publish from your AI chat.
Related MCP Servers
- FlicenseAqualityFmaintenanceEnables AI assistants to interact with Confluence Cloud for managing spaces, pages, and content via the Model Context Protocol (MCP).1115-
- AlicenseAqualityDmaintenanceIntegrates with Atlassian Cloud products (Confluence and Jira) to enable AI assistants to search, read, create, and manage pages, issues, comments, attachments, and export content through natural language interactions.40MIT
- FlicenseAqualityDmaintenanceEnables AI assistants to create, update, delete, and search Confluence pages directly through natural language commands in Cursor, with support for space management and page history.172-
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Atlassian Confluence and Jira through natural language, allowing users to search, create, update, and transition issues and pages.MIT