CVE-2026-27826
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…
Does this matter?
EPSS puts the probability of exploitation in the next 30 days at 13.6%, higher than 96% of all known CVEs. Patch or mitigate before the next change window.
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.
- CVSS 3.1
- 8.2 HIGHCVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
- EPSS
- 13.63% probability · 96th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-918
- Affected
- sooperset/mcp atlassian
- Source
- security-advisories@github.com
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.