AI Safety Testing Program Brief

Introduction

Welcome to the OneMCP AI Safety Program. Through this program, we aim to ensure our AI systems align with ethical guidelines, safety standards, and fairness principles. We invite security researchers, AI experts, and human testers to help us identify and mitigate potential risks in our AI models and systems.

Model Context Protocol (MCP)

The Model Context Protocol is an open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools

About OneMCP

Getting tired of cloning repos, setting them up, and debugging nonsense just to run a simple MCP?

OneMCP is an app that lets you run any MCP without the complexity of downloading repos, reading docs, or setting up servers. - with hundreds available out of the box. And yeah, it's completely FREE.

Scope

In-Scope Systems & Models

onemcp.io AI components

Out-of-Scope Systems

Non AI components or standard software vulnerabilities

Vulnerability Types

Bias & Fairness Issues: AI models displaying or reinforcing harmful biases.
Security Risks: Prompt injection, human attacks, or data poisoning.
Hallucination & Misinformation: AI generating misleading or harmful outputs.
Privacy Violations: Unintended exposure of user data or model training data.
Autonomy & Control Issues: AI taking unintended actions beyond its designed capabilities.

Submission Guidelines

Provide a clear and detailed description of the vulnerability.
Include reproducible steps or a proof-of-concept.
Explain the potential impact and suggest possible mitigations.
Submit via the feedback form.

Responsible Disclosure

Do not publicly disclose the vulnerability before we resolve the issue.
Only test systems within the defined scope.
Do not exploit vulnerabilities beyond what is necessary to demonstrate the issue.

Legal Considerations

Participants must comply with applicable laws and ethical guidelines. OneMCP reserves the right to determine eligibility and bounty rewards.

Contact

For any inquiries or clarifications, please reach out to programs@pointlessai.com.

Thank you for helping us create safer and more aligned AI systems!