CVE-2026-77244: CWE-287: Improper Authentication in sooperset mcp-atlassian
CVE-2026-77244 is an improper authentication vulnerability in the MCP Atlassian server used for Atlassian products like Confluence and Jira. Versions prior to 0.22.0 accept HTTP requests without verifying user identity, causing the server to use the operator's global Jira or Confluence credentials for downstream operations. This allows any network client with access to the MCP endpoint to perform read and write actions as the operator. The vulnerability is fixed in version 0.22.0.
AI Analysis
Technical Summary
MCP Atlassian is a Model Context Protocol server for Atlassian products. Before version 0.22.0, its HTTP transport layer does not verify user identities on incoming requests. When authentication is missing, the system falls back to using the operator's globally configured Jira or Confluence credentials for downstream fetcher construction. This flaw enables an attacker who can reach the MCP endpoint to invoke Atlassian tools with the operator's privileges, including read and write capabilities. The vulnerability involves components such as UserTokenMiddleware, AtlassianOpaqueTokenVerifier, _get_fetcher, and streamable-http. The issue is resolved in version 0.22.0.
Potential Impact
An unauthenticated network attacker with access to the MCP endpoint can perform actions on Atlassian tools (Confluence and Jira) with the operator's privileges, including reading and modifying data. This represents a critical security risk due to the high level of access granted without authentication.
Mitigation Recommendations
Upgrade MCP Atlassian to version 0.22.0 or later, where this improper authentication vulnerability is fixed. No other mitigation is indicated by the vendor advisory.
CVE-2026-77244: CWE-287: Improper Authentication in sooperset mcp-atlassian
Description
CVE-2026-77244 is an improper authentication vulnerability in the MCP Atlassian server used for Atlassian products like Confluence and Jira. Versions prior to 0.22.0 accept HTTP requests without verifying user identity, causing the server to use the operator's global Jira or Confluence credentials for downstream operations. This allows any network client with access to the MCP endpoint to perform read and write actions as the operator. The vulnerability is fixed in version 0.22.0.
CVSS v3.1
Score 10.0critical
Affected software
sooperset
mcp-atlassian
pkg:github/sooperset/mcp-atlassianRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
MCP Atlassian is a Model Context Protocol server for Atlassian products. Before version 0.22.0, its HTTP transport layer does not verify user identities on incoming requests. When authentication is missing, the system falls back to using the operator's globally configured Jira or Confluence credentials for downstream fetcher construction. This flaw enables an attacker who can reach the MCP endpoint to invoke Atlassian tools with the operator's privileges, including read and write capabilities. The vulnerability involves components such as UserTokenMiddleware, AtlassianOpaqueTokenVerifier, _get_fetcher, and streamable-http. The issue is resolved in version 0.22.0.
Potential Impact
An unauthenticated network attacker with access to the MCP endpoint can perform actions on Atlassian tools (Confluence and Jira) with the operator's privileges, including reading and modifying data. This represents a critical security risk due to the high level of access granted without authentication.
Mitigation Recommendations
Upgrade MCP Atlassian to version 0.22.0 or later, where this improper authentication vulnerability is fixed. No other mitigation is indicated by the vendor advisory.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-08-20T19:02:23.416Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6ab2c2eff7a7c541068b81de
Added to database: 09/22/2026, 18:03:27 UTC
Last enriched: 09/22/2026, 18:17:45 UTC
Last updated: 09/22/2026, 18:56:21 UTC
Views: 5
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.