Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). This integration supports both Atlassian Cloud and Jira Server/Data Center deployments.
Product | Deployment Type | Support Status |
---|---|---|
Confluence | Cloud | ✅ Fully supported |
Confluence | Server/Data Center | ❌ Not yet supported |
Jira | Cloud | ✅ Fully supported |
Jira | Server/Data Center | ✅ Supported (version 8.14+) |
On macOS:
brew install uv
When using uv
, no specific installation is needed. We will use uvx
to directly run mcp-atlassian.
uvx mcp-atlassian
Alternatively you can install mcp-atlassian via pip:
pip install mcp-atlassian
To install Atlassian Integration for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-atlassian --client claude
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
- Generate a Personal Access Token in your Jira Server/Data Center (version 8.14 or later):
- Navigate to your profile by clicking on your avatar in the top right corner
- Select Profile → Personal Access Tokens (Alternative path in some versions: Account Settings → Security → Personal Access Tokens)
- Click Create token
- Give your token a meaningful name (e.g., "MCP Integration")
- Set an expiry date (or choose "Never" if permitted by your organization)
- Copy the generated token immediately (you won't be able to see it again)
Note: For all configuration methods, include only the environment variables needed for your services:
- For Confluence only (Cloud): Include
CONFLUENCE_URL
,CONFLUENCE_USERNAME
, andCONFLUENCE_API_TOKEN
- For Jira Cloud: Include
JIRA_URL
,JIRA_USERNAME
, andJIRA_API_TOKEN
- For Jira Server/Data Center: Include
JIRA_URL
andJIRA_PERSONAL_TOKEN
- For multiple services: Include the variables for each service you want to use
Using uvx
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "[email protected]",
"CONFLUENCE_API_TOKEN": "your_api_token",
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_USERNAME": "[email protected]",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}
For Jira Server/Data Center:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "[email protected]",
"CONFLUENCE_API_TOKEN": "your_api_token",
"JIRA_URL": "https://jira.your-company.com",
"JIRA_PERSONAL_TOKEN": "your_personal_access_token"
}
}
}
}
Using pip
{
"mcpServers": {
"mcp-atlassian": {
"command": "python",
"args": ["-m", "mcp-atlassian"],
"env": {
"CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "[email protected]",
"CONFLUENCE_API_TOKEN": "your_api_token",
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_USERNAME": "[email protected]",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}
Using docker
There are two ways to configure the Docker environment:
- Using environment variables directly in the config:
{
"mcpServers": {
"mcp-atlassian": {
"command": "docker",
"args": ["run", "--rm", "-i", "mcp/atlassian"],
"env": {
"CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "[email protected]",
"CONFLUENCE_API_TOKEN": "your_api_token",
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_USERNAME": "[email protected]",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}
- Using an environment file:
{
"mcpServers": {
"mcp-atlassian": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--env-file",
"/path/to/your/.env",
"mcp/atlassian"
]
}
}
}
The .env file should contain:
CONFLUENCE_URL=https://your-domain.atlassian.net/wiki
CONFLUENCE_USERNAME=[email protected]
CONFLUENCE_API_TOKEN=your_api_token
JIRA_URL=https://your-domain.atlassian.net
JIRA_USERNAME=[email protected]
JIRA_API_TOKEN=your_api_token
To integrate the MCP server with Cursor IDE:
Configure the server:
- Open Cursor Settings
- Navigate to
Features
>MCP Servers
- Click
Add new MCP server
- Enter this configuration:
name: mcp-atlassian type: command command: uvx mcp-atlassian --confluence-url=https://your-domain.atlassian.net/wiki [email protected] --confluence-token=your_api_token --jira-url=https://your-domain.atlassian.net [email protected] --jira-token=your_api_token
If you've cloned the repository and want to run a local version of mcp-atlassian
:
Configure in Claude Desktop:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uv",
"args": [
"--directory", "/path/to/your/mcp-atlassian",
"run", "mcp-atlassian",
"--confluence-url=https://your-domain.atlassian.net/wiki",
"[email protected]",
"--confluence-token=your_api_token",
"--jira-url=https://your-domain.atlassian.net",
"[email protected]",
"--jira-token=your_api_token"
]
}
}
}
Note: The MCP server filters resources to only show Confluence spaces and Jira projects that the user is actively interacting with, based on their contributions and assignments.
confluence://{space_key}
: Access Confluence spacesjira://{project_key}
: Access Jira projects
Tool | Description |
---|---|
confluence_search |
Search Confluence content using CQL |
confluence_get_page |
Get content of a specific Confluence page |
confluence_get_comments |
Get comments for a specific Confluence page |
confluence_create_page |
Create a new Confluence page |
confluence_update_page |
Update an existing Confluence page |
jira_get_issue |
Get details of a specific Jira issue |
jira_search |
Search Jira issues using JQL |
jira_get_project_issues |
Get all issues for a specific Jira project |
jira_create_issue |
Create a new issue in Jira |
jira_update_issue |
Update an existing Jira issue |
jira_delete_issue |
Delete an existing Jira issue |
jira_get_transitions |
Get available status transitions for a Jira issue |
jira_transition_issue |
Transition a Jira issue to a new status |
jira_add_worklog |
Add a worklog entry to a Jira issue |
jira_get_worklog |
Get worklog entries for a Jira issue |
jira_link_to_epic |
Link an issue to an Epic |
jira_get_epic_issues |
Get all issues linked to a specific Epic |
You can use the MCP inspector to debug the server:
npx @modelcontextprotocol/inspector uvx mcp-atlassian
For development installations:
cd path/to/mcp-atlassian
npx @modelcontextprotocol/inspector uv run mcp-atlassian
View logs with:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
Docker build:
docker build -t mcp/atlassian .
- 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.