CVE-2026-77261: CWE-918: Server-Side Request Forgery (SSRF) in sooperset mcp-atlassian
CVE-2026-77261 is a Server-Side Request Forgery (SSRF) vulnerability in the MCP Atlassian server component for Atlassian products like Confluence and Jira. Versions prior to 0.22.0 omit a safety hook in certain session branches, allowing attacker-controlled redirects to internal addresses without proper validation. This can lead to unauthorized internal network access. The issue is fixed in version 0.22.0.
AI Analysis
Technical Summary
MCP Atlassian is a Model Context Protocol server used with Atlassian products. In versions before 0.22.0, the _make_ssrf_safe_hook function is missing from JiraFetcher and ConfluenceFetcher sessions created via basic-auth and oauth_pat branches. This omission allows sessions to follow redirects returned by a compromised or attacker-controlled Atlassian instance to internal addresses without revalidating the destination, resulting in a Server-Side Request Forgery (CWE-918) vulnerability. The vulnerability is resolved in version 0.22.0.
Potential Impact
An attacker who can control or compromise a configured Atlassian instance may exploit this vulnerability to cause the MCP Atlassian server to make unauthorized requests to internal network addresses. This can lead to unauthorized information disclosure (high confidentiality impact) and partial integrity loss, but does not affect availability. The CVSS 3.1 score is 7.1 (high severity) reflecting network attack vector, high complexity, low privileges required, no user interaction, and scope change.
Mitigation Recommendations
Upgrade MCP Atlassian to version 0.22.0 or later where the vulnerability is fixed by including the _make_ssrf_safe_hook in the affected session branches. No other mitigations are specified. Patch status is confirmed fixed in version 0.22.0.
CVE-2026-77261: CWE-918: Server-Side Request Forgery (SSRF) in sooperset mcp-atlassian
Description
CVE-2026-77261 is a Server-Side Request Forgery (SSRF) vulnerability in the MCP Atlassian server component for Atlassian products like Confluence and Jira. Versions prior to 0.22.0 omit a safety hook in certain session branches, allowing attacker-controlled redirects to internal addresses without proper validation. This can lead to unauthorized internal network access. The issue is fixed in version 0.22.0.
CVSS v3.1
Score 7.1high
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.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
MCP Atlassian is a Model Context Protocol server used with Atlassian products. In versions before 0.22.0, the _make_ssrf_safe_hook function is missing from JiraFetcher and ConfluenceFetcher sessions created via basic-auth and oauth_pat branches. This omission allows sessions to follow redirects returned by a compromised or attacker-controlled Atlassian instance to internal addresses without revalidating the destination, resulting in a Server-Side Request Forgery (CWE-918) vulnerability. The vulnerability is resolved in version 0.22.0.
Potential Impact
An attacker who can control or compromise a configured Atlassian instance may exploit this vulnerability to cause the MCP Atlassian server to make unauthorized requests to internal network addresses. This can lead to unauthorized information disclosure (high confidentiality impact) and partial integrity loss, but does not affect availability. The CVSS 3.1 score is 7.1 (high severity) reflecting network attack vector, high complexity, low privileges required, no user interaction, and scope change.
Mitigation Recommendations
Upgrade MCP Atlassian to version 0.22.0 or later where the vulnerability is fixed by including the _make_ssrf_safe_hook in the affected session branches. No other mitigations are specified. Patch status is confirmed fixed in version 0.22.0.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-08-20T19:02:23.417Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6ab2c670f7a7c541068f922e
Added to database: 09/22/2026, 18:18:24 UTC
Last enriched: 09/22/2026, 18:32:42 UTC
Last updated: 09/22/2026, 19:34:28 UTC
Views: 6
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.