MCPSafe.io
RegistryThreatsMethodologyDocsPricingScanSign in

Legal

Terms of Service

Last updated: May 5, 2026

These terms are written in plain English. If you need the full legal version for your company, email info@mcpsafe.io.

Contents

  1. 1. What MCPSafe is
  2. 2. Acceptable use
  3. 3. Scan results disclaimer
  4. 4. Data and privacy
  5. 5. Service availability
  6. 6. Account termination
  7. 7. Limitation of liability
  8. 8. Governing law
  9. 9. Contact

1. What MCPSafe is

MCPSafe ("Service") provides automated security assessments of MCP (Model Context Protocol) servers. Our scores are informational — not legal or security advice. We use heuristics, static analysis, and AI models. A high score does not guarantee safety; apply your own judgement before deploying any package in production.

2. Acceptable use

You may use MCPSafe to:

  • Scan MCP servers before installing them
  • Integrate our API into your development workflow
  • Share scan results publicly

You may NOT:

  • Scan packages you do not have rights to analyse (e.g. private packages without authorisation)
  • Use the API to build a competing scanner service without our written consent
  • Attempt to reverse-engineer our scoring algorithm or scrape our database
  • Submit packages containing data designed to attack our infrastructure
  • Circumvent or evade rate limits via automation, multiple accounts, or similar means
  • Use the Service to harass or defame any package maintainer

3. Scan results disclaimer

MCPSafe provides automated security assessments based on heuristics, static analysis, and AI models. Our scores are not guarantees. A high score does not mean a package is safe; a low score does not mean it is malicious. Always apply your own judgement. MCPSafe is not liable for damage caused by packages you install after viewing a scan result.

AI-generated content notice. Some parts of a scan result are produced by large language models — including the per-finding remediation advice, the overall safety explanation, and the LLM consensus panel verdicts on deep-mode scans. LLM output can be incorrect, incomplete, or hallucinated. Treat it as a starting point for your own review, not a substitute for it. Do not rely on MCPSafe's LLM output as the sole basis for production-grade or security-critical decisions.

Scan grades are informational and do not constitute an automated individual decision with legal or similarly significant effect within the meaning of Art. 22 GDPR. You retain full control over whether to install any package.

4. Data and privacy

We store your scan history. Scans of the same package are shared in our cache — your identity is never revealed to other users. See our Privacy Policy for full details.

5. Service availability

MCPSafe offers a free tier and paid plans — see Pricing. We aim for 99.5% uptime but provide no SLA guarantee.

6. Account termination

  • You can delete your account at any time from /settings.
  • We may suspend accounts that violate these terms, with 24-hour notice except for severe violations (e.g. active attack on our infrastructure).

7. Limitation of liability

To the maximum extent permitted by German law (BGB §309), MCPSafe's liability is limited to the fullest extent allowed by applicable law. We are not liable for indirect, incidental, or consequential damages arising from use of the Service.

8. Governing law

These terms are governed by German law. Disputes go to the courts of Essen, Germany. EU consumers retain the right to use the courts of their country of residence.

9. Contact

Legal questions: info@mcpsafe.io | MCPSafe | Essen, Germany

Privacy PolicyCookie Policy← Home
MCPSafe.io

Security checks for MCP servers — public packages and private repos, fast or deep.

Legal

Privacy PolicyCookie PolicyTerms of ServiceSecurity disclosure

Resources

State of MCP SecuritySupportSystem statusMade in Germany 🇩🇪

© 2026 MCPSafe. All rights reserved.

GDPR — Privacy Policy