9.6
CRITICAL CVSS 3.1
CVE-2025-6514
OS command injection in mcp-remote when connecting to untrusted MCP servers
Description

mcp-remote is exposed to OS command injection when connecting to untrusted MCP servers due to crafted input from the authorization_endpoint response URL

INFO

Published Date :

July 9, 2025, 1:15 p.m.

Last Modified :

July 10, 2025, 1:17 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2025-6514 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
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 CRITICAL [email protected]
Solution
Prevent OS command injection by validating input from authorization_endpoint URLs.
  • Sanitize all inputs from authorization_endpoint.
  • Validate the URL for the authorization endpoint.
  • Update the mcp-remote library to the latest version.
Public PoC/Exploit Available at Github

CVE-2025-6514 has a 47 public PoC/Exploit available at Github. Go to the Public Exploits tab to see the list.

References to Advisories, Solutions, and Tools
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2025-6514 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

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).

Offensive MCP server auditor — detects tool poisoning, credential leaks, RCE vectors, SSRF, session hijacking, and supply chain vulnerabilities across stdio, HTTP, and SSE transports.

ai-security llm-security mcp model-context-protocol offensive-security security supply-chain tool-poisoning vulnerability-scanner mcp-security open-source mcpscan

TypeScript JavaScript

Updated: 11 hours, 22 minutes ago
0 stars 0 fork 0 watcher
Born at : March 10, 2026, 6:30 a.m. This repo has been linked 5 different CVEs too.

Open detection standard for AI agent threats. Like Sigma, but for prompt injection, tool poisoning, and MCP attacks. Community-driven -- contributions welcome.

TypeScript JavaScript

Updated: 4 hours, 43 minutes ago
0 stars 0 fork 0 watcher
Born at : March 9, 2026, 7:48 a.m. This repo has been linked 8 different CVEs too.

ESLint security rules for MCP servers — catches SANDWORM_MODE credential harvesting, path traversal, command injection, and CVE patterns at dev time

TypeScript JavaScript

Updated: 1 day, 2 hours ago
2 stars 0 fork 0 watcher
Born at : March 9, 2026, 1:16 a.m. This repo has been linked 6 different CVEs too.

29 detection rules for AI agent threats across 9 attack categories. Like Sigma, but for prompt injection, tool poisoning, MCP attacks, and skill compromise. RFC status.

agent-security ai-security llm-security mcp-security open-source prompt-injection sigma-rules threat-detection

TypeScript

Updated: 1 day, 3 hours ago
0 stars 0 fork 0 watcher
Born at : March 7, 2026, 4:55 p.m. This repo has been linked 8 different CVEs too.

Agent Interaction Firewall for AI tool calls. Runtime security for MCP and function-calling with <5ms P99, 20+ threat detection layers, formal verification.

ai-agents audit compliance mcp owasp policy-engine rust security agentic-ai ai-security firewall formal-verification mcp-security model-context-protocol tool-calling llm

Dockerfile Makefile JavaScript HTML CSS TypeScript Alloy Rust Lean TLA

Updated: 3 hours, 50 minutes ago
7 stars 1 fork 1 watcher
Born at : Feb. 28, 2026, 4:43 p.m. This repo has been linked 2 different CVEs too.

Zero-dependency MCP security linter — 54 OWASP-mapped checks, 56 malicious packages, 28 CVEs. pip install mcp-config-guard

ai-safety claude-code linter mcp model-context-protocol owasp python sarif security vulnerability-scanner

Python

Updated: 3 days ago
2 stars 0 fork 0 watcher
Born at : Feb. 28, 2026, 4 p.m. This repo has been linked 10 different CVEs too.

Security scanner and runtime protection for MCP (Model Context Protocol) servers

Python

Updated: 1 week, 4 days ago
0 stars 0 fork 0 watcher
Born at : Feb. 27, 2026, 3:30 p.m. This repo has been linked 1 different CVEs too.

Security scanner and runtime protection for MCP (Model Context Protocol) servers

Python

Updated: 1 week, 4 days ago
0 stars 0 fork 0 watcher
Born at : Feb. 27, 2026, 9:07 a.m. This repo has been linked 1 different CVEs too.

None

Python HTML

Updated: 6 days, 3 hours ago
1 stars 0 fork 0 watcher
Born at : Feb. 26, 2026, 8:38 p.m. This repo has been linked 1 different CVEs too.

Org-wide policy enforcement hooks for Claude Code

Shell

Updated: 1 week, 4 days ago
0 stars 0 fork 0 watcher
Born at : Feb. 25, 2026, 5:52 p.m. This repo has been linked 5 different CVEs too.

OpenClaw Security Red Team Framework

Dockerfile JavaScript HTML Shell Python C

Updated: 2 weeks, 2 days ago
0 stars 0 fork 0 watcher
Born at : Feb. 22, 2026, 12:34 p.m. This repo has been linked 2 different CVEs too.

None

TypeScript CSS JavaScript Shell Python

Updated: 2 weeks ago
2 stars 0 fork 0 watcher
Born at : Feb. 21, 2026, 7:27 p.m. This repo has been linked 2 different CVEs too.

MCP security proxy that sits between AI coding assistants and MCP servers, detecting and blocking all known MCP attack classes. Works with any MCP server (tools, resources, prompts) on macOS, Linux, and Windows.

claude linux macos mcp proxy windows mcp-watchdog

Python

Updated: 1 week, 6 days ago
21 stars 0 fork 0 watcher
Born at : Feb. 20, 2026, 8:38 p.m. This repo has been linked 3 different CVEs too.

Enterprise-grade MCP Server Security Toolkit

Python

Updated: 2 weeks, 6 days ago
0 stars 0 fork 0 watcher
Born at : Feb. 18, 2026, 8:01 a.m. This repo has been linked 1 different CVEs too.

None

TypeScript JavaScript

Updated: 3 weeks, 1 day ago
0 stars 0 fork 0 watcher
Born at : Feb. 15, 2026, 10:27 p.m. This repo has been linked 1 different CVEs too.

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2025-6514 vulnerability anywhere in the article.

  • CybersecurityNews
MEDUSA Security Testing Tool With 74 Scanners and 180+ AI Agent Security Rules

MEDUSA, an AI-first Static Application Security Testing (SAST) tool boasting 74 specialized scanners and over 180 AI agent security rules. This open-source CLI scanner targets modern development chall ... Read more

Published Date: Jan 27, 2026 (1 month, 1 week ago)
  • The Hacker News
[Webinar] Securing Agentic AI: From MCPs and Tool Access to Shadow API Key Sprawl

Jan 13, 2026The Hacker NewsArtificial Intelligence / Automation Security AI agents are no longer just writing code. They are executing it. Tools like Copilot, Claude Code, and Codex can now build, t ... Read more

Published Date: Jan 13, 2026 (1 month, 3 weeks ago)
  • CybersecurityNews
Cloudflare Launches MCP Server Portals – A Unified Gateway to All MCP Servers

Cloudflare today launched MCP Server Portals in open beta, a groundbreaking capability designed to centralize, secure, and observe all Model Context Protocol (MCP) connections in an organization. By r ... Read more

Published Date: Aug 28, 2025 (6 months, 1 week ago)
  • The Cloudflare Blog
Securing the AI Revolution: Introducing Cloudflare MCP Server Portals

Securing the AI Revolution: Introducing Cloudflare MCP Server Portals2025-08-266 min read Securing the AI Revolution: Introducing Cloudflare MCP Server Portals Large Language Models (LLMs) are rapidly ... Read more

Published Date: Aug 26, 2025 (6 months, 1 week ago)
  • 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

Published Date: Jul 10, 2025 (8 months ago)
  • CybersecurityNews
Critical mcp-remote Vulnerability Exposes LLM Clients to Remote Code Execution Attacks

A critical vulnerability CVE-2025-6514 with a CVSS score of 9.6 affecting the mcp-remote project allows attackers to achieve arbitrary operating system command execution on machines running mcp-remote ... Read more

Published Date: Jul 10, 2025 (8 months ago)

The following table lists the changes that have been made to the CVE-2025-6514 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.

  • New CVE Received by [email protected]

    Jul. 09, 2025

    Action Type Old Value New Value
    Added Description mcp-remote is exposed to OS command injection when connecting to untrusted MCP servers due to crafted input from the authorization_endpoint response URL
    Added CVSS V3.1 AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
    Added CWE CWE-78
    Added Reference https://github.com/geelen/mcp-remote/commit/607b226a356cb61a239ffaba2fb3db1c9dea4bac
    Added Reference https://jfrog.com/blog/2025-6514-critical-mcp-remote-rce-vulnerability
    Added Reference https://research.jfrog.com/vulnerabilities/mcp-remote-command-injection-rce-jfsa-2025-001290844/
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.
Vulnerability Scoring Details
Base CVSS Score: 9.6
Attack Vector
Attack Complexity
Privileges Required
User Interaction
Scope
Confidentiality Impact
Integrity Impact
Availability Impact