Model Context Protocol (MCP) server for Atlassian Cloud products (Confluence and Jira). This integration is designed specifically for Atlassian Cloud instances and does not support Atlassian Server or Data Center deployments.
confluence://{space_key}: Access Confluence spaces and pagesconfluence://{space_key}/pages/{title}: Access specific Confluence pagesjira://{project_key}: Access Jira project and its issuesjira://{project_key}/issues/{issue_key}: Access specific Jira issues
-
confluence_search- Search Confluence content using CQL
- Inputs:
query(string): CQL query stringlimit(number, optional): Results limit (1-50, default: 10)
- Returns: Array of search results with page_id, title, space, url, last_modified, type, and excerpt
-
confluence_get_page- Get content of a specific Confluence page
- Inputs:
page_id(string): Confluence page IDinclude_metadata(boolean, optional): Include page metadata (default: true)
- Returns: Page content and optional metadata
-
confluence_get_comments- Get comments for a specific Confluence page
- Input:
page_id(string): Confluence page ID
- Returns: Array of comments with author, creation date, and content
-
jira_get_issue- Get details of a specific Jira issue
- Inputs:
issue_key(string): Jira issue key (e.g., 'PROJ-123')expand(string, optional): Fields to expand
- Returns: Issue details including content and metadata
-
jira_search- Search Jira issues using JQL
- Inputs:
jql(string): JQL query stringfields(string, optional): Comma-separated fields (default: "*all")limit(number, optional): Results limit (1-50, default: 10)
- Returns: Array of matching issues with metadata
-
jira_get_project_issues- Get all issues for a specific Jira project
- Inputs:
project_key(string): Project keylimit(number, optional): Results limit (1-50, default: 10)
- Returns: Array of project issues with metadata
-
Clone the Repository:
git clone https://github.com/pashpashpash/mcp-atlassian.git cd mcp-atlassian -
Install Dependencies:
npm install
-
Build the Project:
npm run build
The MCP Atlassian integration supports using either Confluence, Jira, or both services. You only need to provide the environment variables for the service(s) you want to use.
-
Get API tokens from: https://id.atlassian.com/manage-profile/security/api-tokens
-
Add to your
claude_desktop_config.jsonwith only the services you need:
For Confluence only:
{
"mcpServers": {
"mcp-atlassian": {
"command": "node",
"args": ["path/to/build/index.js"],
"env": {
"CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "your.email@domain.com",
"CONFLUENCE_API_TOKEN": "your_api_token"
}
}
}
}For Jira only:
{
"mcpServers": {
"mcp-atlassian": {
"command": "node",
"args": ["path/to/build/index.js"],
"env": {
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_USERNAME": "your.email@domain.com",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}For both services:
{
"mcpServers": {
"mcp-atlassian": {
"command": "node",
"args": ["path/to/build/index.js"],
"env": {
"CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "your.email@domain.com",
"CONFLUENCE_API_TOKEN": "your_api_token",
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_USERNAME": "your.email@domain.com",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}You can use the MCP inspector to debug the server:
cd path/to/mcp-atlassian
npx @modelcontextprotocol/inspector node build/index.jsView logs with:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log- Never share API tokens
- Keep .env files secure and private
- See SECURITY.md for best practices
Licensed under MIT - see LICENSE file. This is not an official Atlassian product.
Note: This is a fork of the original mcp-atlassian repository.