Atlassian

You run a read-only MCP server for Atlassian products to expose Confluence and Jira data to MCP clients. This server lets you fetch pages, spaces, issues, and projects through a lightweight, read-only API safely integrated into your environment.

How to use

To use the Atlassian MCP server, first start the MCP process with the Python runtime using the provided module. Set your Atlassian credentials as environment variables before launching so the server can access Confluence and Jira data.

How to install

Prerequisites you need before installation:

• Python 3.x (recommended) and a working Python environment.

• A suitable directory to install and run the MCP server from.

Additional configuration and usage notes

Configure your Atlassian credentials as environment variables before starting the server. The following variables are used by the MCP server to access Confluence and Jira.

• ATLASSIAN_DOMAIN: your-company.atlassian.net

• ATLASSIAN_EMAIL: your-email@company.com

• ATLASSIAN_CONFLUENCE_TOKEN: your-confluence-token

• ATLASSIAN_JIRA_TOKEN: your-jira-token

Optionally, for backward compatibility you can provide a single token that has access to both services.

• ATLASSIAN_API_TOKEN: your-api-token

If you need to create API tokens, generate them with read-only scopes for reading content and metadata in Confluence and read access plus JQL/search capabilities in Jira. Use separate tokens for Confluence and Jira whenever possible for better security and control.

MCP server configuration example

{
  "mcpServers": {
    "atlassian": {
      "command": "python",
      "args": ["-m", "atlassian_mcp.server"],
      "cwd": "/path/to/your/atlassian_mcp",
      "env": {
        "ATLASSIAN_DOMAIN": "your-company.atlassian.net",
        "ATLASSIAN_EMAIL": "your-email@company.com",
        "ATLASSIAN_CONFLUENCE_TOKEN": "your-confluence-token",
        "ATLASSIAN_JIRA_TOKEN": "your-jira-token"
      }
    }
  }
}

Tools and endpoints overview

The server provides a set of read-only tools to retrieve Atlassian data. These tools correspond to Confluence pages, spaces, and Jira issues and projects. Each tool is designed to fetch data based on identifiers like IDs, URLs, or search queries.

Available tools

confluence_get_page

Retrieve a Confluence page by its ID. Returns page content and metadata suitable for display or indexing.

confluence_get_page_by_url

Fetch a Confluence page using its URL. Useful when you have a direct link to a page.

confluence_search_pages

Search Confluence pages using keywords, metadata, or CQL-like queries to locate relevant content.

confluence_list_spaces

List all Confluence spaces available to the authenticated account.

jira_get_issue

Get Jira issue details by its key (for example PROJ-123).

jira_get_issue_by_url

Fetch a Jira issue using its direct URL.

jira_search_issues

Search Jira issues using JQL to filter by project, status, assignee, and more.

jira_list_projects

List all Jira projects visible to the authenticated user.