CVE-2026-77249
Received Received - Intake

Server-Side Request Forgery in MCP Atlassian Prior to 0.22.0

Publication date: 2026-09-22

Last updated on: 2026-09-22

Assigner: GitHub, Inc.

Description
MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to 0.22.0, JiraUserMixin._lookup_user_by_permissions uses the module-level requests.get function instead of the fetcher's protected session. A caller-controlled public Jira URL can redirect that unhooked request to an internal address, bypassing the redirect checks added for CVE-2026-27826. The advisory traces the vulnerable input and processing flow through JiraUserMixin._lookup_user_by_permissions, requests.get, self.jira._session.get, and _make_ssrf_safe_hook, which identify the affected entry points, controls, and code paths. This issue is fixed in version 0.22.0.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-22
Last Modified
2026-09-22
Generated
2026-09-22
AI Q&A
2026-09-22
EPSS Evaluated
N/A
NVD
CVE-2026-77249
EUVD
EUVD-2026-84759

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
sooperset mcp-atlassian to 0.22.0 (exc)
atlassian jira to 0.22.0 (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-918 The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This is an SSRF (Server-Side Request Forgery) vulnerability in the MCP Atlassian package before version 0.22.0. It occurs in the JiraUserMixin._lookup_user_by_permissions function, which uses an unhooked requests.get call instead of the protected session. An attacker can exploit this by setting a public Jira URL that redirects to an internal address, bypassing redirect checks and enabling blind SSRF to internal hosts and ports.

Detection Guidance

Check if your mcp-atlassian version is below 0.22.0 by running: pip show mcp-atlassian. If vulnerable, inspect network logs for unexpected outbound requests to internal addresses originating from the mcp-atlassian process.

Impact Analysis

This vulnerability allows unauthenticated attackers to make blind SSRF requests to internal services and ports. While no data exfiltration is possible, it enables internal service reachability and port discovery. Exploitation requires multi-tenant HTTP transport mode and a public base URL controlled by the attacker.

Compliance Impact

This vulnerability enables blind SSRF to internal hosts and ports, which could allow unauthorized network reconnaissance or interaction with internal services. Such access may violate data protection requirements under GDPR (e.g., unauthorized access to personal data) and HIPAA (e.g., unauthorized access to protected health information) by exposing internal systems that process sensitive data.

Mitigation Strategies

Upgrade mcp-atlassian to version 0.22.0 or later immediately. If immediate upgrade is not possible, restrict outbound network access for the mcp-atlassian process to prevent SSRF exploitation.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-77249. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart