atlassian-confluence-mcp-server
Description
An open-source Model Context Protocol (MCP) server for Atlassian Confluence that lets AI assistants like Claude and Windsurf read, create, search, and manage Confluence wiki pages. Works with Confluence Cloud, on-premise Server, and Data Center deployments — connect your AI…
About
An open-source Model Context Protocol (MCP) server for Atlassian Confluence that lets AI assistants like Claude and Windsurf read, create, search, and manage Confluence wiki pages. Works with Confluence Cloud, on-premise Server, and Data Center deployments — connect your AI coding agent to your team's knowledge base…
Details
- Author
- anuragagrawal0430
- Categories
- Productivity, Other, Knowledge Base, Communication, Project Management
Jump to
Setup
Install atlassian-confluence-mcp-server in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/anuragagrawal0430/atlassian-confluence-mcp-server
Follow the installation instructions in the repository README, then restart your MCP client.
An open-source Model Context Protocol (MCP) server for Atlassian Confluence that lets AI assistants like Claude and Windsurf read, create, search, and manage Confluence wiki pages. Works with Confluence Cloud, on-premise Server, and Data Center deployments — connect your AI coding agent to your team's knowledge base in seconds via npx.
An open-sourceModel Context Protocol (MCP)serverforAtlassian Confluencethat lets AI assistants likeClaudeandWindsurfread, create, search, and manage Confluence wiki pages. Works withConfluence Cloud,on-premise Server, andData Centerdeployments — connect your AI coding agent to your team's knowledge base in seconds vianpx.
- ✅ Only MCP server supportingCloud + Server + Data Centerin one package
- ✅47 tools— most comprehensive Confluence MCP available
- ✅ Zero config vianpx— no install needed
- ✅ PAT, Basic Auth, and API token support
- ✅ Actively maintained with provenance-signed releases
Why use this instead of Atlassian's official MCP server?
- Space Management— Create, delete, list, and inspect spaces
- Page CRUD— Create, read, update, delete, copy, and move pages
- Search— Full CQL and text search, recently modified pages
- Labels— Add, list, and remove page labels
- Comments— Read and post page comments
- Attachments— List and upload page and comment attachments
- Page Hierarchy— Navigate parent/child relationships
- Version History— Browse and inspect page versions
- Watchers— View and manage page watchers
- Permissions— Get and set page restrictions
- Tasks— Extract inline tasks from pages
- Export— Generate PDF/Word export URLs
- Personal Space— Create pages in your personal space
- URL Parsing— Retrieve page content from a Confluence URL
- Node.js 18+
- A Confluence instance (Cloud or Server/Data Center 7.9+)
- Authentication credentials (PAT or username/password)
npm install -g atlassian-confluence-mcp-server
git clone https://github.com/anuragagrawal0430/atlassian-confluence-mcp-server.git cd atlassian-confluence-mcp-server npm install npm run build
All configuration is passed throughenvironment variables. Never hard-code credentials.
Cloud API tokens are generated from your Atlassian account and requirebothyour email and the token:
CONFLUENCE_BASE_URL=https://your-site.atlassian.net CONFLUENCE_USERNAME=you@example.com PAT=your-api-token
Server and Data Center instances use a Personal Access Token withBearerauthentication. Only the token is needed:
CONFLUENCE_BASE_URL=https://confluence.example.com PAT=your-personal-access-token
- Navigate toProfile > Settings > Personal Access Tokens
- Create a token with the required permissions
- Copy the token value
For older Server versions without PAT support, use username/password:
CONFLUENCE_BASE_URL=https://confluence.example.com CONFLUENCE_USERNAME=your-username CONFLUENCE_PASSWORD=your-password
The server now uses secure defaults to reduce prompt-injection blast radius and credential leakage risk:
- CONFLUENCE_READ_ONLY=trueby default
- Mutating tools are disabled unless you setCONFLUENCE_READ_ONLY=false.
- confluence_delete_page,confluence_delete_space, andconfluence_set_page_permissionsremain disabled unless explicitly enabled.
- Restrict exposure to an explicit tool allowlist.
- Restrict requests that includespaceKey/destinationSpaceKeyto an approved set.
- HTTPS is required unless this is set totrue.
- Even when enabled, insecure HTTP is restricted to localhost/loopback only.
- Caps how large a host fileconfluence_upload_attachmentwill read before calling Confluence.
- Independent of the instance "Attachment Maximum Size" admin setting (not exposed via public REST).
- Explicitly restricts which host directories the MCP server is allowed to read files from when uploading attachments.
- If not configured, file uploads from the host filesystem are entirely disabled.
Example (enable safe writes, keep destructive tools disabled):
CONFLUENCE_READ_ONLY=false CONFLUENCE_ENABLE_DESTRUCTIVE_TOOLS=false
CONFLUENCE_ENABLED_TOOLS=confluence_get_page,confluence_search_pages,confluence_get_page_body_chunk
{ "mcpServers": { "confluence": { "command": "npx", "args": ["-y", "atlassian-confluence-mcp-server"], "env": { "CONFLUENCE_BASE_URL": "https://your-site.atlassian.net", "CONFLUENCE_USERNAME": "you@example.com", "PAT": "your-api-token" } } } }
{ "mcpServers": { "confluence": { "command": "npx", "args": ["-y", "atlassian-confluence-mcp-server"], "env": { "CONFLUENCE_BASE_URL": "https://confluence.example.com", "PAT": "your-personal-access-token" } } } }
{ "mcpServers": { "confluence": { "command": "atlassian-confluence-mcp-server", "env": { "CONFLUENCE_BASE_URL": "https://confluence.example.com", "PAT": "your-personal-access-token" } } } }
{ "mcpServers": { "confluence": { "command": "node", "args": ["./dist/index.js"], "env": { "CONFLUENCE_BASE_URL": "https://confluence.example.com", "PAT": "your-personal-access-token" } } } }
Note: tool exposure depends on security configuration. With the defaultCONFLUENCE_READ_ONLY=true, mutating tools are intentionally hidden/blocked.
# Pages in a specific space type=page AND space=TEAM # Pages with a label type=page AND label=documentation # Recently modified pages type=page AND lastModified > now("-7d") # Title search type=page AND title~"Meeting Notes" # Pages created by current user type=page AND creator=currentUser()
Pages use Confluence storage format (XHTML):
<p>This is a paragraph.</p> <h1>Heading 1</h1> <ul> <li>Item 1</li> <li>Item 2</li> </ul> <ac:structured-macro ac:name="code"> <ac:parameter ac:name="language">javascript</ac:parameter> <ac:plain-text-body><![CDATA[console.log("Hello");]]></ac:plain-text-body> </ac:structured-macro>
When a page body is very large (for example hundreds of KB), avoid sending the full body throughconfluence_update_page.
- Useconfluence_get_page_body_chunkto inspect the relevant part of the page.
- Use one of:
- confluence_patch_pagefor exact find/replace edits.
- confluence_replace_page_rangefor replacing a specific middle range.
- confluence_append_to_pagefor incremental append/prepend updates.
- Offset-based range replacement is the most reliable mode for storage XHTML.
- Line-based replacement requires actual newline characters in the stored body.
- These tools still perform a full Confluence update under the hood, but the full body remains server-side.
- Credentialsare read exclusively from environment variables — never hard-coded.
- Input validation— all user-supplied parameters are validated and sanitized before use.
- CQL injection prevention— user input interpolated into CQL queries is escaped.
- URL path encoding— all dynamic path segments are encoded withencodeURIComponent.
- Request timeouts— all HTTP requests have a 30-second timeout to prevent hanging.
- Error sanitization— API error responses are truncated and stripped of HTML before surfacing.
- Pagination limits— query limits are clamped to a safe maximum (100) to prevent abuse.
Please seeCONTRIBUTING.mdfor guidelines on how to contribute to this project.
For security policies and vulnerability reporting, seeSECURITY.md.
SeeCHANGELOG.mdfor a history of changes.
- Model Context Protocol
- Atlassian Confluence REST API
Interact with Atlassian Confluence Cloud spaces, pages, and content in real-time.
Provides secure access to Atlassian Confluence content and spaces using its REST API.
Interact with the Confluence API to manage spaces, pages, and content. Supports searching, creating, and updating pages.
An MCP server that enables AI assistants to interact with Confluence content through a standardized interface.
Atlassian Rovo MCP Server (Streamin HTTP)
Integrate with Atlassian Cloud to access Jira tickets, issues, projects, and Confluence pages.
A read-only server for accessing Atlassian products like Confluence and Jira.
Manage Confluence Cloud spaces, pages, and content through a standardized interface for AI assistants.
Server for hybrid search over locally saved and indexed Confluence content in AI clients.
An open-source collaborative wiki and documentation software with AI integration via MCP.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
