CVE-2025-49596
Published: 13 June 2025
Summary
CVE-2025-49596 is a critical-severity Missing Authentication for Critical Function (CWE-306) vulnerability in Thenewstack (inferred from references). Its CVSS base score is 9.4 (Critical).
Operationally, ranked in the top 15.2% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.
Deeper analysis
The MCP Inspector is a developer tool used for testing and debugging MCP servers. Versions below 0.14.1 contain a remote code execution vulnerability stemming from missing authentication between the Inspector client and proxy, which permits unauthenticated requests to execute MCP commands over stdio. The flaw is tracked as CWE-306 and carries a CVSS 4.0 score of 9.4.
An attacker with network access can exploit the issue by sending crafted requests to the unauthenticated proxy interface, resulting in arbitrary command execution with high impact to confidentiality, integrity, and availability, plus scope change. No user interaction or privileges are required beyond the ability to reach the exposed component.
Public advisories and the associated GitHub security advisory direct users to upgrade immediately to version 0.14.1 or later; a patch commit addressing the authentication gap is referenced in the repository.
The vulnerability pertains to the Model Context Protocol ecosystem used in AI tooling, with coverage highlighting risks around untrusted code execution in such environments. EPSS rose from a low baseline to a recorded peak of 0.0412, indicating emerging exploitation interest after disclosure.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-20870
Vulnerability details
The MCP inspector is a developer tool for testing and debugging MCP servers. Versions of MCP Inspector below 0.14.1 are vulnerable to remote code execution due to lack of authentication between the Inspector client and proxy, allowing unauthenticated requests to…
more
launch MCP commands over stdio. Users should immediately upgrade to version 0.14.1 or later to address these vulnerabilities.
- 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: mcp
Related Threats
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Requires established identification and authentication to unlock, mitigating missing authentication for continued system access.
Requiring identification and rationale for actions allowed without authentication ensures critical functions are not left unprotected by forcing review of authentication requirements.
Authorizing mobile device connections to organizational systems ensures authentication is performed for this critical access function.
Guarantees critical functions are protected by mandatory invocation of the access control mechanism.
Auditing sessions makes it possible to detect access to critical functions without required authentication.
The assessment process confirms authentication is present and effective for critical functions, preventing exploitation from missing authentication.
Certification assesses that critical functions have required authentication controls in place.
Disabling non-essential functions and services eliminates the need to secure them, reducing exposure from missing authentication on unnecessary components.