Skip to main content
Press slash or control plus K to focus the search. Use the arrow keys to navigate results and press enter to open a threat.
Reconnecting to live updates…
EPSS 0.2%top 88%

CVE-2026-44428: CWE-918: Server-Side Request Forgery (SSRF) in modelcontextprotocol registry

0
Low
VulnerabilityCVE-2026-44428cvecve-2026-44428cwe-918
Published: Thu May 14 2026 (05/14/2026, 21:09:10 UTC)
Source: CVE Database V5
Vendor/Project: modelcontextprotocol
Product: registry

Description

CVE-2026-44428 is a Server-Side Request Forgery (SSRF) vulnerability in the modelcontextprotocol (MCP) registry versions prior to 1.7.6. The issue arises because the GitHub OIDC token audience is globally fixed rather than bound to a specific registry instance, allowing tokens obtained from one MCP registry deployment to be accepted by others sharing the same code and audience string. This could lead to unauthorized actions based on repository ownership permissions. The vulnerability has a low severity score and is fixed in version 1.7.6.

CVSS v4.0

Score 2.1low

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
Present
Privileges Required
None
User Interaction
Active
Vuln. Confidentiality
None
Vuln. Integrity
Low
Vuln. Availability
None
Subsq. Confidentiality
None
Subsq. Integrity
Low
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:A/VC:N/VI:L/VA:N/SC:N/SI:L/SA:N

Affected software

Affected versions
<1.7.6

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 05/22/2026, 15:36:59 UTC

Technical Analysis

The MCP Registry acts as a directory for MCP servers. Before version 1.7.6, the GitHub OIDC flow for both client and server sides uses a global audience string ('mcp-registry') rather than a unique audience per registry instance. Clients always request tokens with this fixed audience, and servers validate tokens only against this audience, deriving permissions from repository ownership. Consequently, a token legitimately obtained from one MCP registry deployment can be reused to interact with any other deployment sharing the same codebase and audience string, potentially allowing unauthorized access or actions. This vulnerability is addressed by binding the OIDC flow to the specific registry instance in version 1.7.6.

Potential Impact

An attacker with a token from one MCP registry deployment could use it to access or perform actions on other MCP registry deployments that share the same code and audience string. This could lead to unauthorized repository publishing permissions being granted across deployments. However, the overall impact is limited by the low CVSS score (2.1) and the requirement for user interaction to obtain tokens.

Mitigation Recommendations

Upgrade MCP registry deployments to version 1.7.6 or later, where the GitHub OIDC flow is properly bound to the specific registry instance, preventing token reuse across deployments. Since no official patch link or remediation level is provided beyond this version update, users should verify with the vendor for the latest guidance. Patch status is not explicitly confirmed in the advisory, so check vendor sources for current remediation details.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-05-06T14:40:00.953Z
Cvss Version
4.0
State
PUBLISHED
Remediation Level
null

Threat ID: 6a0643eeec166c07b0159681

Added to database: 5/14/2026, 9:51:42 PM

Last enriched: 5/22/2026, 3:36:59 PM

Last updated: 6/18/2026, 12:55:04 AM

Views: 87

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses