MCP server for Atlassian

MCP server for Atlassian is an application that provides AI assistants with access to Jira and Confluence via the standard Model Context Protocol (MCP). The server is deployed on a virtual machine in Yandex Cloud.

Key Features and Benefits

• Yandex AI Studio Integration. The MCP server integrates with AI Studio MCP Servers — connect it to your AI agents in just a few clicks.
• Jira Integration. Enables AI assistants to search issues, create and update tasks, manage projects, and view statuses via natural language.
• Confluence Integration. Search and read pages, create and update content in Confluence spaces using an AI assistant.
• Cloud and Server/Data Center Support. Works with both Atlassian Cloud and self-hosted Jira Server/Data Center.
• Bearer Token Authorization. All requests to the MCP server are protected with a Bearer token stored in Yandex Lockbox.
• Secure Secret Storage. Atlassian credentials (API tokens, personal tokens) are stored in Yandex Lockbox and retrieved at startup.
• Standard MCP Protocol. Uses the open Model Context Protocol for AI model interaction.
• HTTP Transport. The MCP server is accessible on port 8000 (HTTP).
• Minimal Resources. The application runs on a virtual machine with minimal configuration (2 vCPU, 2 GB RAM).
• Docker Containerization. The server runs in Docker containers (MCP + nginx auth proxy).

1. Make sure you have access to Jira and/or Confluence (Cloud or Server/Data Center).
2. For Atlassian Cloud: create an API token for your Atlassian account.
3. For Server/Data Center: create a Personal Access Token in your profile settings.
4. Create a secret in Yandex Lockbox to store Atlassian credentials. The secret must contain keys depending on the connection type:
   • For Confluence Cloud: confluence_username (email) and confluence_api_token.
   • For Confluence Server/Data Center: confluence_personal_token.
   • For Jira Cloud: jira_username (email) and jira_api_token.
   • For Jira Server/Data Center: jira_personal_token.
5. Create a secret in Yandex Lockbox to store the Bearer token for authorization. The secret must contain a bearer_token key with an arbitrary token value.
6. Create a service account with the roles compute.editor, iam.serviceAccounts.admin, lockbox.payloadViewer, vpc.admin (the admin role includes all the specified roles).
7. In the management console select the Cloud Apps service.
8. In the left panel, select Application Store.
9. Select MCP Atlassian and click the Use button.
10. Specify:
    • Application name.
    • (Optional) Application description.
    • The service account created earlier.
    • The cloud subnet where the virtual machine will be deployed.
    • Lockbox secret ID containing the Bearer token for authorization.
    • Confluence URL (if used).
    • Jira URL (if used).
    • Lockbox secret ID containing Atlassian credentials.
11. Click the Install button and wait for the application to install.
12. After installation, the MCP server will be available at http://<vm-ip>:8000.
13. Configure your AI client (Claude Desktop, Cursor, etc.) to connect to the MCP server, specifying the Authorization: Bearer <your-token> header.

Connecting the MCP server to Yandex AI Studio

1. In the management console open the AI Studio service and go to the MCP Hub section.
2. Click Create MCP server and choose the External MCP server type.
3. Specify the server name and the ID of the VPC network where the MCP server virtual machine is deployed. The network ID is available on the application page in the Application data section, VPC network ID field.
4. At the MCP server connection step, fill in the parameters with the values from the Application data section:
   • MCP server type — value from the MCP server type field.
   • MCP server URL — value from the MCP server URL (internal) field.
   • In the HTTP headers block, add an Authorization header with the value Bearer <bearer_token>, where <bearer_token> is the token from the Yandex Lockbox secret specified during application installation.
5. Click Connect. After a successful connection check, select the required tools and click Connect — the MCP server will be registered in AI Studio and available for use by AI agents.

• Searching Jira issues using an AI assistant (Claude, ChatGPT).
• Creating and updating Jira issues via natural language.
• Searching and reading Confluence pages.
• Creating and editing Confluence content through an AI assistant.
• Managing projects and tracking issue statuses in Jira.

Yandex Cloud technical support is available 24/7. The types of requests you can submit and the appropriate response time depend on your pricing plan. You can switch to the paid support plan in the management console. You can learn more about the technical support terms here.