Raw vector
CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:NCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-27826 is a high-severity SSRF (CWE-918) vulnerability in Sooperset Mcp Atlassian. Its CVSS base score is 8.2 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 4% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.
The strongest mitigations our analysis identified map to AC-4 (Information Flow Enforcement) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
MCP Atlassian is a Model Context Protocol (MCP) server designed for integration with Atlassian products such as Confluence and Jira. Versions prior to 0.17.0 contain a vulnerability (CVE-2026-27826, CWE-918) that allows an unauthenticated attacker to force the server process to make outbound HTTP requests to arbitrary attacker-controlled URLs. This server-side request forgery (SSRF) issue arises in the HTTP middleware and dependency injection layer, rather than in MCP tool handlers, rendering it undetectable by tool-level code analysis. The vulnerability has a CVSS v3.1 score of 8.2 (AV:A/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N).
An unauthenticated attacker with adjacent network access to the mcp-atlassian HTTP endpoint can exploit this by supplying two custom HTTP headers without an Authorization header. Successful exploitation enables the attacker to conduct internal network reconnaissance from the server's perspective. In cloud deployments, it facilitates theft of IAM role credentials by targeting the instance metadata endpoint at 169.254.169.254. Across any HTTP deployment, it allows injection of attacker-controlled content into LLM tool results.
The GitHub security advisory (GHSA-7r34-79r5-rcc9) and fixing commit (5cd697dfce9116ef330b8dc7a91291640e0528d9) confirm that upgrading to version 0.17.0 resolves the issue.
This vulnerability is particularly relevant to AI/ML deployments, as MCP servers bridge LLMs with enterprise tools, potentially exposing LLM integrations to SSRF-based content manipulation or credential theft. No real-world exploitation has been reported.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-10788
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: llm, mcp, model context protocol
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.6V1.5.3V5.3.2V10.4.7
Mitigating Controls (NIST 800-53 r5) AI
Information flow enforcement can restrict which destinations the server is allowed to contact on behalf of users.
Input validation directly stops untrusted URLs from being accepted and fetched without destination checks.
Boundary protection limits the network reach of server-initiated requests even if SSRF occurs.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure development practices directly include input validation and destination allow-listing that prevent SSRF.
Runtime monitoring of web applications and services can detect anomalous outbound requests indicative of SSRF.
Vulnerability identification processes can discover and record SSRF flaws in web applications.
Network segmentation and egress controls can limit the damage from successful SSRF requests.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Operational threat data describing SSRF campaigns can be used to tighten outbound-request allow-lists and detection rules before attackers exploit them.