Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). This integration supports both Confluence & Jira Cloud and Server/Data Center deployments.
Ask your AI assistant to:
- 📝 Automatic Jira Updates - "Update Jira from our meeting notes"
- 🔍 AI-Powered Confluence Search - "Find our OKR guide in Confluence and summarize it"
- 🐛 Smart Jira Issue Filtering - "Show me urgent bugs in PROJ project from last week"
- 📄 Content Creation & Management - "Create a tech design doc for XYZ feature"
mcp-atlassian-jira-demo.mp4
Confluence Demo
confluence-1k.mp4
Product | Deployment Type | Support Status |
---|---|---|
Confluence | Cloud | ✅ Fully supported |
Confluence | Server/Data Center | ✅ Supported (version 6.0+) |
Jira | Cloud | ✅ Fully supported |
Jira | Server/Data Center | ✅ Supported (version 8.14+) |
First, generate the necessary authentication tokens for Confluence & Jira:
- Go to https://id.atlassian.com/manage-profile/security/api-tokens
- Click Create API token, name it
- Copy the token immediately
- Go to your profile (avatar) → Profile → Personal Access Tokens
- Click Create token, name it, set expiry
- Copy the token immediately
The primary way to use MCP Atlassian is through IDE integration:
Option 1: Using uvx (Recommended)
Install uv first:
macOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
With uv
installed, you can use uvx mcp-atlassian
directly in your IDE configuration without installing the package separately.
Option 2: Using pip
pip install mcp-atlassian
Option 3: Using Smithery
npx -y @smithery/cli install mcp-atlassian --client claude
When configuring in your IDE, you can use these optional environment variables:
CONFLUENCE_SPACES_FILTER
: Filter by space keys (e.g., "DEV,TEAM,DOC")JIRA_PROJECTS_FILTER
: Filter by project keys (e.g., "PROJ,DEV,SUPPORT")READ_ONLY_MODE
: Set to "true" to disable write operationsMCP_VERBOSE
: Set to "true" for more detailed logging
Note: You can configure just Confluence, just Jira, or both services by including only the variables for the services you need.
See the .env.example file for all available options.
MCP Atlassian is designed to be used with AI assistants through IDE integration.
Note: To apply the configuration in Claude Desktop:
Method 1 (Recommended): Click hamburger menu (☰) > Settings > Developer > "Edit Config" button
Method 2: Locate and edit the configuration file directly:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Linux:
~/.config/Claude/claude_desktop_config.json
For Cursor: Open Settings → Features → MCP Servers → + Add new global MCP server
Here's how to set it up based on your installation method:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "your.email@company.com",
"CONFLUENCE_API_TOKEN": "your_api_token",
"JIRA_URL": "https://your-company.atlassian.net",
"JIRA_USERNAME": "your.email@company.com",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}
Server/Data Center Configuration
For Server/Data Center deployments, use these environment variables instead:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"CONFLUENCE_URL": "https://confluence.your-company.com",
"CONFLUENCE_PERSONAL_TOKEN": "your_token",
"JIRA_URL": "https://jira.your-company.com",
"JIRA_PERSONAL_TOKEN": "your_token"
}
}
}
}
Single Service Configurations
For Confluence only:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "your.email@company.com",
"CONFLUENCE_API_TOKEN": "your_api_token"
}
}
}
}
For Jira only:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"JIRA_URL": "https://your-company.atlassian.net",
"JIRA_USERNAME": "your.email@company.com",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}
Alternative: Using CLI Arguments
You can also use command-line arguments instead of environment variables:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": [
"mcp-atlassian",
"--confluence-url=https://your-company.atlassian.net/wiki",
"--confluence-username=your.email@company.com",
"--confluence-token=your_api_token",
"--jira-url=https://your-company.atlassian.net",
"--jira-username=your.email@company.com",
"--jira-token=your_api_token"
]
}
}
}
Using pip
If you've installed mcp-atlassian with pip, use this configuration instead:
{
"mcpServers": {
"mcp-atlassian": {
"command": "mcp-atlassian",
"env": {
"CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "your.email@company.com",
"CONFLUENCE_API_TOKEN": "your_api_token",
"JIRA_URL": "https://your-company.atlassian.net",
"JIRA_USERNAME": "your.email@company.com",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}
Using SSE Instead of stdio
- Start the server with:
uvx mcp-atlassian --transport sse --port 9000 \
--confluence-url https://your-company.atlassian.net/wiki \
--confluence-username your.email@company.com \
--confluence-token your_api_token \
--jira-url https://your-company.atlassian.net \
--jira-username your.email@company.com \
--jira-token your_api_token
- Configure in your IDE:
{
"mcpServers": {
"mcp-atlassian-sse": {
"url": "http://localhost:9000/sse"
}
}
}
confluence://{space_key}
: Access Confluence spacesjira://{project_key}
: Access Jira projects
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_search
: Search Confluence content using CQLconfluence_get_page
: Get content of a specific pageconfluence_create_page
: Create a new pageconfluence_update_page
: Update an existing pageconfluence_attach_content
: Attach content to a page
jira_get_issue
: Get details of a specific issuejira_search
: Search issues using JQLjira_create_issue
: Create a new issuejira_update_issue
: Update an existing issuejira_transition_issue
: Transition an issue to a new statusjira_add_comment
: Add a comment to an issue
View All Tools
Confluence Tools | Jira Tools |
---|---|
confluence_search |
jira_get_issue |
confluence_get_page |
jira_search |
confluence_get_page_children |
jira_get_project_issues |
confluence_get_page_ancestors |
jira_get_epic_issues |
confluence_get_comments |
jira_create_issue |
confluence_create_page |
jira_batch_create_issues |
confluence_update_page |
jira_update_issue |
confluence_delete_page |
jira_delete_issue |
confluence_attach_content |
jira_get_transitions |
jira_transition_issue |
|
jira_add_comment |
|
jira_add_worklog |
|
jira_get_worklog |
|
jira_download_attachments |
|
jira_link_to_epic |
|
jira_get_agile_boards |
|
jira_get_board_issues |
|
jira_get_sprints_from_board |
|
jira_get_sprint_issues |
|
jira_create_issue_link |
|
jira_remove_issue_link |
- Authentication Failures:
- For Cloud: Check your API tokens (not your account password)
- For Server/Data Center: Verify your personal access token is valid and not expired
- For older Confluence servers: Some older versions require basic authentication with
CONFLUENCE_USERNAME
andCONFLUENCE_API_TOKEN
(where token is your password)
- SSL Certificate Issues: If using Server/Data Center and encounter SSL errors, set
CONFLUENCE_SSL_VERIFY=false
orJIRA_SSL_VERIFY=false
- Permission Errors: Ensure your Atlassian account has sufficient permissions to access the spaces/projects
# Using MCP Inspector for testing
npx @modelcontextprotocol/inspector uvx mcp-atlassian ...
# For local development version
npx @modelcontextprotocol/inspector uv --directory /path/to/your/mcp-atlassian run mcp-atlassian ...
# View logs
# macOS
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
# Windows
type %APPDATA%\Claude\logs\mcp*.log | more
- Never share API tokens
- Keep .env files secure and private
- See SECURITY.md for best practices
We welcome contributions to MCP Atlassian! If you'd like to contribute:
- Check out our CONTRIBUTING.md guide
- Set up your development environment:
uv sync --frozen --all-extras --dev pre-commit install
- Make changes and submit a pull request
We use pre-commit hooks for code quality and follow semantic versioning for releases.
Licensed under MIT - see LICENSE file. This is not an official Atlassian product.