CyberRota Analysis
AI-GeneratedThe vulnerability allows unauthorized access to the HTTP MCP endpoint in MCP Atlassian servers for Confluence and Jira, enabling attackers to perform operations with elevated permissions using globally configured credentials. This critical flaw affects all deployments prior to version 0.22.0 that lack an independent authentication boundary. Organizations utilizing these Atlassian products should prioritize patching to version 0.22.0 to mitigate the risk of unauthorized access and potential data breaches.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to 0.22.0, requests to the HTTP MCP endpoint without a per-user identity are allowed to reach tool handlers, which then use globally configured Jira or Confluence credentials. A network caller can perform operations with the operator account's permissions unless the deployment has an independent authentication boundary. The advisory traces the vulnerable input and processing flow through streamable-http, UserTokenMiddleware, _get_fetcher, and global credentials, which identify the affected entry points, controls, and code paths. This issue is fixed in version 0.22.0.
Related CVEs
Other vulnerabilities affecting the same vendor(s)