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 :

April 15, 2026, 12:35 a.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 83 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).

Cursor + Claude plugin for AAAA-Nexus MCP: 7 skills for UEP governance, RatchetGate / MCP trust boundary, Vanguard on-chain, Aegis proxy, evidence chains. BSL 1.1.

Python

Updated: 5 hours, 36 minutes ago
0 stars 0 fork 0 watcher
Born at : April 20, 2026, 2:10 p.m. This repo has been linked 1 different CVEs too.

The most comprehensive LLM + MCP security guide i.e. OWASP aligned, real CVEs, actionable checklists

ai-security claude cybersecurity generative-ai infosec jailbreak langchain llm-security mcp-security openai owasp prompt-injection red-teaming

Updated: 1 day, 13 hours ago
2 stars 0 fork 0 watcher
Born at : April 18, 2026, 6:37 p.m. This repo has been linked 6 different CVEs too.

Hybrid classical + post-quantum (NIST FIPS 204 ML-DSA-65) digital receipts for AI agent decisions. First production MCP server with offline-verifiable post-quantum signing.

ai-agents ai-safety cnsa-2 cryptographic-receipts cryptography crystals-dilithium ed25519 eu-ai-act fips-204 mcp ml-dsa-65 model-context-protocol owasp-asi post-quantum-cryptography prompt-injection-defense python responsible-ai agentic-diffusion cve-2026-25253 trustatom

Python

Updated: 2 days, 16 hours ago
0 stars 0 fork 0 watcher
Born at : April 18, 2026, 2:30 a.m. This repo has been linked 7 different CVEs too.

Autonomous Sovereign System: Atomadic Development Environment.

Python JavaScript Jupyter Notebook

Updated: 13 hours, 58 minutes ago
0 stars 0 fork 0 watcher
Born at : April 17, 2026, 12:09 a.m. This repo has been linked 1 different CVEs too.

A practitioner-focused reference for AI/ML security — attacks, tools, research, and defenses. Covers offensive AI, securing AI systems, AI-assisted security operations, and governance.

Updated: 1 week, 1 day ago
0 stars 0 fork 0 watcher
Born at : April 12, 2026, 4:30 p.m. This repo has been linked 28 different CVEs too.

Enterprise integration patterns: idempotent event processing, saga orchestration, transactional outbox, and webhook validation for reliable system-of-record sync

crm enterprise-architecture enterprise-integration event-driven integration-patterns salesforce workflow-automation agentic-ai cloud-integration data-integration fastapi idempotency kafka mcp-security microservices oracle python saga-pattern state-machine transactional-outbox

Python

Updated: 2 days, 23 hours ago
0 stars 0 fork 0 watcher
Born at : April 10, 2026, 7:27 p.m. This repo has been linked 1 different CVEs too.

Formally verified AI safety APIs for autonomous agents. 78+ endpoints, x402 USDC micropayments, MCP server, A2A protocol. Proof verifier included.

Shell

Updated: 1 week, 4 days ago
0 stars 0 fork 0 watcher
Born at : April 9, 2026, 1:16 p.m. This repo has been linked 1 different CVEs too.

🤖 Curated AI OSINT resources — Google dorks, Shodan queries, GitHub dorks, and techniques to discover exposed LLM endpoints, leaked AI API keys, misconfigured vector databases, and unprotected AI agents

ai-osint ai-security api-keys artificial-intelligence bug-bounty cybersecurity google-dorks hacking llm-security machine-learning mcp-security ollama osint owasp pentesting prompt-injection reconnaissance red-team shodan vector-database

Updated: 2 days, 23 hours ago
18 stars 0 fork 0 watcher
Born at : April 8, 2026, 2:08 p.m. This repo has been linked 3 different CVEs too.

None

Python

Updated: 1 week, 1 day ago
0 stars 0 fork 0 watcher
Born at : April 8, 2026, 3:11 a.m. This repo has been linked 1 different CVEs too.

A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.

ai-agent-security ai-agents ai-security awesome-list cybersecurity llm-security mcp-security prompt-injection supply-chain-security adversarial-attacks agent-security agentic-ai ai-attacks ai-safety cve incident-response owasp red-team security-research vulnerability

Updated: 3 days, 2 hours ago
6 stars 1 fork 1 watcher
Born at : April 7, 2026, 2:19 p.m. This repo has been linked 46 different CVEs too.

Formally verified AI safety APIs for autonomous agents. 75+ endpoints, x402 USDC micropayments, MCP server, A2A protocol. No signup required.

a2a ai-agents autonomous-agents base-l2 cloudflare-workers formal-verification llm mcp usdc x402

Updated: 1 week, 6 days ago
1 stars 0 fork 0 watcher
Born at : April 7, 2026, 1:18 p.m. This repo has been linked 1 different CVEs too.

Open source AI agent security toolkit, MCP tool poisoning scanner, ghost agent detection, prompt injection patterns. OWASP Agentic Top 10 2026.

Python

Updated: 4 days, 18 hours ago
0 stars 0 fork 0 watcher
Born at : April 6, 2026, 10:43 a.m. This repo has been linked 1 different CVEs too.

Runtime security proxy for MCP servers — the open-source firewall between AI agents and tools

Dockerfile Go

Updated: 2 weeks, 1 day ago
0 stars 0 fork 0 watcher
Born at : April 4, 2026, 10:33 p.m. This repo has been linked 5 different CVEs too.

MCP server security audit tool — detects tool poisoning (CVE-2025-6514), prompt injection, and unsafe patterns. 13 tests.

ai-agents llm mcp model-context-protocol python security

Python

Updated: 2 weeks, 6 days ago
0 stars 0 fork 0 watcher
Born at : March 31, 2026, 8:46 a.m. This repo has been linked 1 different CVEs too.

A modular cybersecurity guide mapping prompt injection attack surfaces across all Claude environments

Python Shell

Updated: 2 weeks, 6 days ago
0 stars 0 fork 0 watcher
Born at : March 30, 2026, 10:04 p.m. This repo has been linked 3 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 (2 months, 3 weeks 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 (3 months, 1 week 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 (7 months, 3 weeks 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 (7 months, 3 weeks 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 (9 months, 1 week 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 (9 months, 1 week 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.