Server-side Request Forgery (SSRF) Affecting mcp-atlassian package, versions [,0.17.0)


Severity

Recommended
0.0
medium
0
10

CVSS assessment by Snyk's Security Team. Learn more

Threat Intelligence

Exploit Maturity
Proof of Concept
EPSS
13.63% (97th percentile)

Do your applications use this vulnerable package?

In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.

Test your applications

Snyk Learn

Learn about Server-side Request Forgery (SSRF) vulnerabilities in an interactive lesson.

Start learning
  • Snyk IDSNYK-PYTHON-MCPATLASSIAN-15518738
  • published13 Mar 2026
  • disclosed10 Mar 2026
  • creditGil Maman, yotampe-pluto

Introduced: 10 Mar 2026

CVE-2026-27826  (opens in a new tab)
CWE-918  (opens in a new tab)

How to fix?

Upgrade mcp-atlassian to version 0.17.0 or higher.

Overview

mcp-atlassian is a The Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Atlassian tools while maintaining data privacy and security. Key features include:

Affected versions of this package are vulnerable to Server-side Request Forgery (SSRF) via the HTTP endpoint. An attacker can cause the server to make arbitrary outbound HTTP requests to attacker-controlled URLs, potentially exposing sensitive internal resources or credentials, by sending specially crafted requests containing X-Atlassian-Jira-Url or X-Atlassian-Confluence-Url headers without an Authorization header.

Note:

This is only exploitable if the server is running with --transport streamable-http or --transport sse, the request contains both the relevant URL and personal token headers, and no Authorization header is present.

CVSS Base Scores

version 4.0
version 3.1