Vulnerability · Published Mar 10, 2026 · Assigned by GitHub_M
CVE-2026-27826MCP Atlassian has SSRF via unvalidated X-Atlassian-Jira-Url / X-Atlassian-Confluence-Url headers
High 8.2
In plain English
A high-severity server-side request forgery in mcp-atlassian from sooperset. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 13.9% (higher than 97% of all known vulnerabilities). Ready-made attack tooling exists: Nuclei. Fixed versions are available - upgrade the affected package.
Official description
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | mcp-atlassian | 0.17.0 | GHSA-7r34-79r5-rcc9 |
| PyPI | mcp-atlassian | 0.17.0 | PYSEC-2026-2621 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| sooperset | mcp-atlassian | < 0.17.0 |
Weakness: CWE-918 · Vector: CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N