What is the CVSS score of CVE-2026-27826?

CVE-2026-27826 has a CVSS 3.1 base score of 8.2 (High). CVSS vector: CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N. EPSS exploitation probability: 0.0%.

Which versions of Atlassian are affected by CVE-2026-27826?

A HIGH severity vulnerability (CVE-2026-27826) affects MCP Atlassian servers used to integrate Confluence and Jira with AI/automation tools.. A patch is available.

Is there a public PoC exploit available for CVE-2026-27826?

Yes, a public proof-of-concept exploit is available for CVE-2026-27826. Prioritise patching immediately. EPSS: 0.0%.

How to fix or mitigate CVE-2026-27826?

Within 24 hours: Audit all instances of MCP Atlassian servers in production and development environments; disable the service if non-critical or isolate it from external networks. Within 7 days: Implement network segmentation to restrict MCP server access to authorized internal systems only; review access logs for suspicious activity. Within 30 days: Monitor vendor communications for patch release; evaluate alternative integration solutions or MCP server alternatives; conduct security assessment of affected systems.

Atlassian CVE-2026-27826

HIGH

Server-Side Request Forgery (SSRF) (CWE-918)

2026-03-10 security-advisories@github.com

GHSA-7r34-79r5-rcc9

Atlassian SSRF

8.2

CVSS 3.1 · GitHub Advisory

Severity by source

GitHub Advisory PRIMARY

8.2 HIGH

AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N

Attack Vector

Adjacent

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Changed

Confidentiality

High

Integrity

Low

Availability

None

Lifecycle Timeline

Patch released

Mar 31, 2026 - 21:13 nvd

Patch available

Analysis Generated

Mar 12, 2026 - 21:55 vuln.today

CVE Published

Mar 10, 2026 - 19:17 nvd

HIGH 8.2

DescriptionGitHub Advisory

MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to version 0.17.0, an unauthenticated attacker who can reach the mcp-atlassian HTTP endpoint can force the server process to make outbound HTTP requests to an arbitrary attacker-controlled URL by supplying two custom HTTP headers without an Authorization header. No authentication is required. The vulnerability exists in the HTTP middleware and dependency injection layer - not in any MCP tool handler - making it invisible to tool-level code analysis. In cloud deployments, this could enable theft of IAM role credentials via the instance metadata endpoint (169[.]254[.]169[.]254). In any HTTP deployment it enables internal network reconnaissance and injection of attacker-controlled content into LLM tool results. Version 0.17.0 fixes the issue.

AnalysisAI

Unauthenticated attackers can abuse the MCP Atlassian server to perform arbitrary outbound HTTP requests by manipulating HTTP headers, enabling credential theft from cloud instance metadata endpoints or internal network reconnaissance without requiring authentication. The vulnerability exists in the HTTP middleware layer prior to version 0.17.0, affecting Atlassian Confluence and Jira deployments. No patch is currently available.

Technical ContextAI

Classified as CWE-918 (Server-Side Request Forgery (SSRF)). MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to version 0.17.0, an unauthenticated attacker who can reach the mcp-atlassian HTTP endpoint can force the server process to make outbound HTTP requests to an arbitrary attacker-controlled URL by supplying two custom HTTP headers without an Authorization header. No authentication is required. The vulnerability exists in the HTTP middleware and dependency injection layer — not in any MCP t