Atlassian MCP Server

Atlassian MCP Server provides integration with popular Atlassian tools — Jira and Confluence, through the MCP (Marketplace Connector Protocol). The product supports both Atlassian Cloud deployments and on-premises Jira Server/Data Center installations.

Key features:

• Full Jira integration: task management, project management, search and filtering of issues
• Confluence integration: access to knowledge base, search and work with documentation
• Support for various authentication methods:
  • Username and API token (for Atlassian Cloud)
  • Personal Access Token (for Server/Data Center)
  • OAuth 2.0 (for Atlassian Cloud only)
• Flexible configuration through environment variables and secrets
• Ability to work in “read-only” mode for secure access
• Filtering search results by Jira projects and Confluence spaces

Technical requirements:

• Internet access for connecting to Atlassian Cloud or local network access for connecting to Jira/Confluence Server
• Port 8000 for API server access
• Credentials for authentication in Jira and/or Confluence

1. Create a service account and assign it the lockbox.payloadViewer role;
2. In Marketplace, find the MCP Atlassian Server product and click Install;
3. In the Additional section, specify the previously created service account;
4. In the Product Configuration section:
   • In the Jira URL field, enter the URL of your Jira instance (e.g., https://your-domain.atlassian.net or https://jira.your-company.com);
   • In the Jira Username field, enter the username or email for Jira Cloud;
   • In the Confluence URL field, enter the URL of your Confluence instance (e.g., https://your-domain.atlassian.net/wiki);
   • In the Confluence Username field, enter the username or email for Confluence Cloud;
5. Select a subnet with configured Internet access and create a security group with allowed port 8000;
6. Create a virtual machine;
7. After installation:
   • The API server will be available at http://<VM IP address>:8000;
   • To verify functionality, execute a test request:

   curl --location 'http://<VM IP address>:8000/mcp/' \
   --header 'Accept: application/json, text/event-stream' \
   --header 'Content-Type: application/json' \
   --data '{
     "jsonrpc": "2.0",
     "id": 1,
     "method": "initialize",
     "params": {
       "protocolVersion": "2024-11-05",
       "capabilities": {},
       "clientInfo": {
         "name": "client",
         "version": "1.0.0"
       }
     }
   }'
   

Integration with task management system:

User: I need to create a new task in our development project.
MCP Atlassian: What type of task would you like to create?
User: A bug in the authorization module.
MCP Atlassian: Please describe the issue.
User: Users cannot log in to the system after the update.
MCP Atlassian: Task PROJ-123 “Bug in authorization module” has been created and assigned to the development team.

Searching for information in the knowledge base

User: How do I set up integration with the payment system API?
MCP Atlassian: Searching in Confluence… Found document “Integration with payment systems”. According to the documentation, you need to obtain an API key in the payment system’s personal account, then add it to the integration settings in the “Payments” section.
User: Show me the full instructions.
MCP Atlassian: Displaying full instructions from Confluence: [detailed step-by-step instructions with code and examples].

Project status monitoring

User: What’s the status of our current sprint?
MCP Atlassian: Current sprint “Release 2.5” ends in 3 days. Progress: 15 tasks completed, 5 in progress, 2 blocked. Forecasted completion: 95%.
User: Which tasks are blocked?
MCP Atlassian: Blocked tasks: PROJ-456 “API performance optimization” — waiting for response from infrastructure team; PROJ-789 “Integration with external service” — waiting for partner API access.

Yandex Cloud technical support is available 24/7 to respond to requests. The types of requests available and their response time depend on your pricing plan. You can activate paid support in the management console. Learn more about requesting technical support.

Yandex Cloud does not provide technical support for this product. If you have any issues, please refer to the developer’s information resources.