Confluence
About
Integrates with Atlassian Confluence to enable direct retrieval, searching, creation, and updating of wiki pages without switching contexts.
Details
- Author
- cosmix
- Repository
- cosmix/confluence-mcp
- GitHub stars
- 2
- License
- MIT License
- Categories
- Productivity, Other, Knowledge Base, Communication, Developer Tools, Design, Workplace, File Management, AI, Search, Security, Infrastructure
Jump to
- Authenticate to Confluence using a personal API token
- Retrieve and search Confluence pages and spaces
- Create and update Confluence content
- Retrieve and add comments to pages
- Retrieve and add attachments to pages
- Clean and transform Confluence content for AI consumption
- Handle API communication, error handling, and data transformation
- Basic rate limiting to prevent API abuse
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ConfluenceCommand (node, npx, python, etc.)bunArguments-
Argument 1
/absolute/path/to/confluence-mcp/dist/index.js
Environment-
CONFLUENCE_BASE_URL
your_confluence_instance_url/wiki -
CONFLUENCE_API_TOKEN
your_api_token -
CONFLUENCE_USER_EMAIL
your_email
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
To use this MCP server, you need to set the following environment variables:
CONFLUENCE_API_TOKEN=your_api_token
CONFLUENCE_BASE_URL=your_confluence_instance_url # e.g., https://your-domain.atlassian.net/wiki
CONFLUENCE_USER_EMAIL=your_email
bun install
Add this configuration to your settings file:
{
"mcpServers": {
"confluence": {
"command": "bun",
"args": ["/absolute/path/to/confluence-mcp/dist/index.js"],
"env": {
"CONFLUENCE_API_TOKEN": "your_api_token",
"CONFLUENCE_BASE_URL": "your_confluence_instance_url/wiki",
"CONFLUENCE_USER_EMAIL": "your_email"
}
}
}
}
get_page
Retrieve a Confluence page by ID. Parameters: pageId (string), format (string, can be 'text' or 'markdown'), includeMarkup (boolean)
search_pages
Search for Confluence pages using CQL. Parameters: query (string), limit (integer), format (string, can be 'text' or 'markdown'), includeMarkup (boolean)
get_spaces
List all available Confluence spaces. Parameters: limit (integer)
create_page
Create a new Confluence page. Parameters: spaceKey (string), title (string), content (string, in XHTML format), parentId (optional string)
update_page
Update an existing Confluence page. Parameters: pageId (string), title (string), content (string, in XHTML format), version (integer)
get_comments
Retrieve comments for a specific Confluence page. Parameters: pageId (string), limit (integer), format (string, can be 'text' or 'markdown')
add_comment
Add a comment to a Confluence page. Parameters: pageId (string), content (string), parentId (optional string)
get_attachments
Retrieve attachments for a specific Confluence page. Parameters: pageId (string), limit (integer)
add_attachment
Add an attachment to a Confluence page. Parameters: pageId (string), filename (string), fileContentBase64 (string), comment (string)
The Confluence MCP server exposes the following tools:
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"confluence": {
"env": {
"CONFLUENCE_BASE_URL": "your_confluence_instance_url/wiki",
"CONFLUENCE_API_TOKEN": "your_api_token",
"CONFLUENCE_USER_EMAIL": "your_email"
},
"args": [
"/absolute/path/to/confluence-mcp/dist/index.js"
],
"command": "bun"
}
}
}
Linux
{
"env": {
"CONFLUENCE_BASE_URL": "your_confluence_instance_url/wiki",
"CONFLUENCE_API_TOKEN": "your_api_token",
"CONFLUENCE_USER_EMAIL": "your_email"
},
"args": [
"/absolute/path/to/confluence-mcp/dist/index.js"
],
"command": "bun"
}
Macos
{
"env": {
"CONFLUENCE_BASE_URL": "your_confluence_instance_url/wiki",
"CONFLUENCE_API_TOKEN": "your_api_token",
"CONFLUENCE_USER_EMAIL": "your_email"
},
"args": [
"/absolute/path/to/confluence-mcp/dist/index.js"
],
"command": "bun"
}
Windows
{
"env": {
"CONFLUENCE_BASE_URL": "your_confluence_instance_url/wiki",
"CONFLUENCE_API_TOKEN": "your_api_token",
"CONFLUENCE_USER_EMAIL": "your_email"
},
"args": [
"/absolute/path/to/confluence-mcp/dist/index.js"
],
"command": "bun"
}
Confluence MCP
A Model Context Protocol (MCP) server for Confluence, enabling AI assistants to interact with Confluence content through a standardized interface.
ℹ️ There is a separate MCP server for Jira
Features
- Authenticate to Confluence using a personal API token
- Retrieve and search Confluence pages and spaces
- Create and update Confluence content
- Retrieve and add comments to pages
- Retrieve and add attachments to pages
- Clean and transform Confluence content for AI consumption
- Handle API communication, error handling, and data transformation
- Basic rate limiting to prevent API abuse
Prerequisites
- Bun (v1.0.0 or higher)
- Confluence account with API access
Installation
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





