Skip to main content

Atlassian platform MCP server

The Atlassian Platform provides unified access to Jira, Confluence, Bitbucket, and related products. An AI agent with access to Atlassian Platform can manage users and organizations, coordinate work across products, synchronize information, and automate workflows without manual navigation between applications.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.

Before you begin​

You'll need:

  • Access to AI Gateway with permission to create MCP servers
  • API credentials for the application you're connecting (see the relevant application page for what to collect)

Create an MCP server​

Find the API in the catalog​

  1. Sign in to AI Gateway and select MCP Servers from the left navigation.
  2. Select New MCP Server.
  3. Search for the application you want to connect, then select it from the catalog.

Configure the server​

  1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
  2. Enter a Description so your team knows what the server is for.
  3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
  4. Toggle Production mode on if this server will be used in a live workflow.
  5. Select Next.

Configure authentication​

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security​

  1. Set any Rate limits appropriate for your use case and the API's own limits.
  2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
  3. Select Next.

Deploy​

Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

Connect to an AI client​

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

Tips​

  • You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
  • If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
  • You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication​

Atlassian Platform uses OAuth 2.0 authentication. Create an OAuth 2.0 integration at developer.atlassian.com and configure the redirect URI for your AI Gateway. The authorization endpoint is https://auth.atlassian.com/authorize and the token endpoint is https://auth.atlassian.com/oauth/token. Configure scopes based on your needs: read:me, read:jira-user, read:jira-work, write:jira-work, read:confluence-content.all, write:confluence-content, read:bitbucket, write:bitbucket, and others. The API base URL is https://api.atlassian.com.

Available tools​

This MCP server enables cross-product operations, unified user management, and coordination between Jira, Confluence, and Bitbucket without context switching.

ToolDescription
Get current userRetrieve authenticated user profile information
List sitesRetrieve all accessible Atlassian sites
Get siteRetrieve site details and configuration
List usersRetrieve users across the organization
Get userRetrieve specific user profile and permissions
Create userAdd a new user to the organization
Deactivate userDisable a user account
Update user permissionsModify user access and roles
Create groupCreate a user group for permission management
List groupsRetrieve all groups in the organization
Add user to groupAdd a user to a group
Remove user from groupRemove a user from a group
Create Jira issueCreate an issue in Jira from other products
Link issueCreate cross-product links between issues and content
Create Confluence pageCreate documentation from other systems
Update Confluence pageModify Confluence content from AI agent
Embed Jira issueLink Jira issues in Confluence pages
Create pull requestCreate code changes in Bitbucket
List pull requestsRetrieve pull requests across repositories
Link pull request to issueAssociate code changes with Jira issues
Create repositoryCreate a new Bitbucket repository
List repositoriesRetrieve repositories across projects

Tips​

Use organization-scoped tokens for cross-product access — organization-level OAuth tokens can interact with all configured products. Use these for automation that spans multiple Atlassian products.

Link issues to PRs for traceability — when creating pull requests, link them to Jira issues to maintain visibility into which code changes address which work items. This creates end-to-end traceability.

Keep Confluence and Jira synchronized — when updating documentation in Confluence, update related Jira issues to reflect the changes. This prevents stale information in either system.

Store cloud IDs securely and include them in API requests to ensure correct product targeting. Different Atlassian products have different cloud IDs and they are required for API calls.

Monitor usage across products to avoid hitting cumulative limits when making cross-product requests. Each Atlassian product has its own rate limits.