CVE-2025-49596
MCP Inspector proxy server lacks authentication between the Inspector client and proxy
Description
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 launch MCP commands over stdio. Users should immediately upgrade to version 0.14.1 or later to address these vulnerabilities.
INFO
Published Date :
June 13, 2025, 8:15 p.m.
Last Modified :
June 17, 2026, 9:31 a.m.
Remotely Exploit :
Yes !
Source :
[email protected]
Affected Products
The following products are affected by CVE-2025-49596
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 4.0 | CRITICAL | [email protected] |
Solution
- Upgrade MCP Inspector to version 0.14.1 or later.
Public PoC/Exploit Available at Github
CVE-2025-49596 has a 102 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2025-49596.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2025-49596 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2025-49596
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
None
Python
None
Python
Personal exploit library — verified CVE PoCs rewritten from scratch
Python
安全审计与CVE追踪 | Security Audit & CVE Tracking
Clone of https://github.com/modelcontextprotocol/inspector.git with bugs fixed
Dockerfile TypeScript JavaScript HTML CSS
Web-based MCP client with a widget renderer — inspect servers, call tools, and render their UIs the way ChatGPT renders apps. Supports OpenAI Apps SDK & MCP-UI.
HTML TypeScript CSS JavaScript
CIS-Style security audit tool for MCP server deployments — 7 categories, 35+ checks, CVE detection, and actionable remediation.
cis-benchmark mcp security
Python
Static linter for MCP servers and configs. Every rule is pinned to a real CVE with a biting fixture.
ai-agents cve linter mcp model-context-protocol security static-analysis supply-chain
Python
None
Dockerfile Python Shell
Detection-engineering for MCP: working Sigma rules for the OWASP MCP Top 10 + isolated home-lab + zero-dependency validator (git clone && python3 validate.py).
ai-security detection-engineering mcp model-context-protocol owasp purple-team security sigma soc threat-detection
Python
None
Dockerfile Shell Go
Zero-dependency toolkit for authorized security assessment of Model Context Protocol (MCP) servers: enumerate the attack surface, run passive static audits, and opt-in fuzz tool inputs. JSON/Markdown/SARIF reports.
appsec cybersecurity fuzzing infosec mcp model-context-protocol pentesting python sarif security security-tools vulnerability-scanner
Python
Two structural MCP-layer vulnerabilities in Claude Code allowing usage of CC without limitations (tool-result injection, tool-description poisoning).
Shell JavaScript C Makefile
A transparent wiretap for MCP servers — see what your AI client actually sends, without breaking the protocol.
ai-agents anthropic claude cli debugging developer-tools json-rpc llm-tools mcp model-context-protocol observability proxy rust typescript
Rust JavaScript TypeScript Python Shell
An educational, open-source project mapping enterprise AI-agent security end to end: 50 validated risks across an 11-layer deployment, from how an agent is built to how it is retired, with real incidents, solutions, and gaps. Interactive model plus a two-part analysis.
JavaScript CSS HTML
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2025-49596 vulnerability anywhere in the article.
-
Daily CyberSecurity
LiteLLM Under Fire: Triple Threat Vulnerabilities Expose AI Gateways to Total Takeover
LiteLLM, the popular open-source library used to provide a unified interface for over 100 Large Language Models (LLMs) like OpenAI and Anthropic, has been hit with a series of critical security disclo ... Read more
-
Daily CyberSecurity
The Poisoned Pickle: Critical Unpatched RCE Flaws Expose SGLang AI Infrastructure
Security researchers have issued a warning to the AI development community following the discovery of critical vulnerabilities in SGLang, a popular open-source serving framework for Large Language Mod ... Read more
-
The Hacker News
Critical mcp-remote Vulnerability Enables Remote Code Execution, Impacting 437,000+ Downloads
Cybersecurity researchers have discovered a critical vulnerability in the open-source mcp-remote project that could result in the execution of arbitrary operating system (OS) commands. The vulnerabili ... Read more
-
Cyber Security News
Critical Vulnerability in Anthropic MCP Inspector Let Attackers Execute Arbitrary Code
A critical Remote Code Execution (RCE) vulnerability in Anthropic’s MCP Inspector tool, designated as CVE-2025-49596, has a severe CVSS score of 9.4. This vulnerability represents one of the first cri ... Read more
-
The Hacker News
Critical Vulnerability in Anthropic's MCP Exposes Developer Machines to Remote Exploits
Cybersecurity researchers have discovered a critical security vulnerability in artificial intelligence (AI) company Anthropic's Model Context Protocol (MCP) Inspector project that could result in remo ... Read more
-
Daily CyberSecurity
Critical RCE in MCP Inspector Exposes AI Devs to Web-Based Exploits (CVE-2025-49596)
A critical vulnerability—CVE-2025-49596—affected the AI developer ecosystem in June 2025, when Oligo Security Research disclosed a severe Remote Code Execution (RCE) flaw in the MCP Inspector, a core ... Read more
-
Daily CyberSecurity
CVE-2025-49596: Critical RCE Vulnerability in MCP Inspector Exposes AI Developer Environments
A newly disclosed security flaw in the MCP Inspector, a tool designed to test and debug Machine Context Protocol (MCP) servers, could allow unauthenticated remote code execution (RCE) — potentially pu ... Read more
-
Daily CyberSecurity
Two sslh Flaws Disclosed: Remote DoS Attacks Possible via Protocol Multiplexer
In June 2025, the SUSE Security Team disclosed critical vulnerabilities in sslh, a lightweight protocol multiplexer used to serve multiple services—such as SSH and HTTPS—on the same port. Though desig ... Read more
The following table lists the changes that have been made to the
CVE-2025-49596 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by [email protected]
Jun. 17, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'modelcontextprotocol', 'product': 'inspector', 'versions': [{'status': 'affected', 'version': '< 0.14.1'}]}] -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 17, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2025-49596', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2025-06-13T20:32:46.383577Z'} -
CVE Modified by [email protected]
Jul. 09, 2025
Action Type Old Value New Value Added Reference https://thenewstack.io/mcp-vulnerability-exposes-the-ai-untrusted-code-crisis Added Reference https://www.oligo.security/blog/critical-rce-vulnerability-in-anthropic-mcp-inspector-cve-2025-49596 -
New CVE Received by [email protected]
Jun. 13, 2025
Action Type Old Value New Value Added Description 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 launch MCP commands over stdio. Users should immediately upgrade to version 0.14.1 or later to address these vulnerabilities. Added CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CWE CWE-306 Added Reference https://github.com/modelcontextprotocol/inspector/commit/50df0e1ec488f3983740b4d28d2a968f12eb8979 Added Reference https://github.com/modelcontextprotocol/inspector/security/advisories/GHSA-7f8r-222p-6f5g