Skip to main content

Security report for smithery.ai

Technology · Iceland

Medium risk. 5 critical or high findings in Security headers, GDPR outside view and 1 other check.

Security score

64/100

Risk levelMedium

0–100, higher is better. How it is calculated

Smithery.ai is a technology platform specializing in the Model Context Protocol (MCP) registry, enabling AI agents to extend their capabilities by integrating with thousands of community-built skills and extensions. The platform targets developers and AI practitioners seeking to enhance AI agent functionality through a rich ecosystem of MCP servers. The website showcases a variety of MCP servers categorized by functionality such as browser automation, memory management, code collaboration, and web search, providing detailed descriptions and usage guidance. Technically, the website is built using modern web technologies including Next.js and React, hosted with Cloudflare DNS and leveraging Supabase for storage of server icons. The site demonstrates good performance and mobile optimization, with a clean and professional design that facilitates user navigation and discovery of MCP servers. Analytics are implemented via a third-party service (dubcdn.com), indicating minimal user tracking. From a security perspective, the site employs HTTPS and domain transfer protection but lacks DNSSEC and published security policies or incident response information. No critical vulnerabilities or exposed sensitive data were detected. Privacy compliance is limited as no privacy or cookie policies are present, which is a notable gap for GDPR and related regulations. Overall, Smithery.ai presents a credible and specialized platform for AI agent extension, with solid technical infrastructure but room for improvement in privacy and security transparency. Strategic enhancements in policy publication and security headers would strengthen trust and compliance.

Scanned

NIS2 and GDPR posture

GDPR outside view
53/ 100 · Medium
Checks completed
7of 7

NIS2 Art. 21(2)

  1. (a) Risk analysis and security policies: Not visible from outside
  2. (b) Incident handling: One indicator
  3. (c) Business continuity, backups and crisis management: Not visible from outside
  4. (d) Supply chain security: Not visible from outside
  5. (e) Secure acquisition, development and maintenance, including vulnerability handling: Partly checked
  6. (f) Assessing the effectiveness of security measures: Not visible from outside
  7. (g) Cyber hygiene and security training: Not visible from outside
  8. (h) Cryptography and encryption: Partly checked
  9. (i) HR security, access control and asset management: One indicator
  10. (j) Multi-factor authentication and secured communications: Not visible from outside

This scan rated NIS2 with an earlier keyword method that is no longer shown; rescan for the per-article view. Risk management, continuity, supply chain, training, MFA, management oversight (Art. 20) and incident reporting (Art. 23) need internal evidence, and Guard cannot tell whether NIS2 applies to this organisation.

GDPR is indicative only, based on publicly visible signals: Articles 7, 12, 13 and 32 of Regulation (EU) 2016/679 and Article 5(3) of the ePrivacy Directive. Not a certification or legal assessment.

Priority findings

5 findings rated critical or high. Fix these first.

  1. Security headers

    Security headers are instructions your web server sends to every visitor’s browser. Missing ones leave visitors more exposed to attacks such as clickjacking and injected scripts.

    • High

      Missing X-Frame-Options header

      Prevents clickjacking attacks

      What to do: Add "X-Frame-Options: DENY" or "X-Frame-Options: SAMEORIGIN"

    • High

      Missing Content-Security-Policy header

      Controls resources the browser is allowed to load

      What to do: Implement a Content-Security-Policy appropriate for your application

      • ASVS V3.4.3
      • OWASP Secure Headers: OWASP Secure Headers Project recommends Content-Security-Policy: default-src 'self'; form-action 'self'; base-uri 'self'; object-src 'none';…

  2. GDPR outside view

    These are the privacy signals visitors and data protection authorities look for under GDPR.

    • High

      No Cookie Policy found

      GDPR requires clear information about cookie usage

      What to do: Add a dedicated cookie policy explaining cookie usage and purposes

    • High

      No Cookie Consent Banner found

      GDPR requires explicit consent for non-essential cookies

      What to do: Implement a cookie consent banner that appears on first visit

  3. SSL/TLS

    TLS encrypts the connection and proves the site is really yours. Weak or expiring certificates trigger browser warnings and put traffic at risk.

    • High

      Weak Protocols Supported

      Server supports weak protocols: TLSv1.1

      What to do: Disable TLS 1.0, TLS 1.1, and all SSL versions

      • CWE-327
      • OWASP A04:2025
      • ASVS V12.1.1

Need hands-on remediation? Email guard@offseq.com

Keep watching smithery.ai

This scan found 27 issues across 6 checks. Monitoring re-runs those checks daily, emails you when something material changes and records each fix, so you can show progress.

Daily monitoring

Recommended

€25per month

  • TLS certificates and expiry
  • DNS records
  • SPF, DKIM and DMARC
  • Security headers
  • GDPR and NIS2 posture
  • Exposed services
  • Third-party trackers
  • Security score drift

Email alerts on material changes and an exportable JSON history of every change.

Billed monthly to your card. Cancel anytime. The full timeline opens with your unlock code.

Full report

€39.90one-time

  • The complete analysis as a PDF you can cite
  • Email delivery with an unlock code
  • Lifetime access to this report

Prices incl. 21% VAT. Secure checkout by Mollie; sold by SEQ SIA, Latvia.

Results by check

Each check with its score, findings and the evidence it collected.

How this score is calculated

The security score runs 0–100, higher is better. It is the plain average of the security checks that completed in this scan, each counted equally. A check that could not run is left out: it counts neither as a pass nor as a fail.

Counted in this score

SSL/TLS
72
Security headers
30
Email security
55
DNS health
75
Network security
100
GDPR outside view
53
Average
64

Not counted

  • NIS2 outside view: Re-weights evidence from the TLS, email, DNS, network and hygiene checks, so counting it would count that evidence twice. Shown on its own.
  • OffSeq Observations: An AI reading of the site, useful context but not reproducible evidence. Shown on its own.

Findings that cap the score at 49

Each of these is serious on its own, so while any is present the site cannot rate better than high risk, however good the other checks are.

  • The certificate is not trusted by browsers
  • The website is not served over HTTPS
  • A database, remote desktop, file-sharing or Telnet service is reachable from the internet
  • The page loads a script from a compromised source
  • The domain registration has expired
  • SPF authorises every server to send mail as the domain

Partial scans

When the site blocks Guard or most checks cannot run, the score covers only the checks that ran (usually DNS and email), is capped at 75 and is shown as partial, without a risk level.

Risk levels

  • Critical0–25
  • High26–49
  • Medium50–75
  • Low76–100

Technical appendix

Business context, site observations and technical notes gathered during the scan, and the standards behind each reference.

Business context

Business profile

Smithery.ai operates in the niche technology sector focused on AI agent integration and extension via the Model Context Protocol. The platform's business model centers on providing a registry and deployment environment for MCP servers, facilitating community contributions and developer adoption. Its market position is that of an emerging startup (founded in 2024) targeting AI developers and organizations building intelligent agents. The platform's competitive advantage lies in its extensive catalog of MCP servers and integration capabilities with popular AI tools like Claude and Cursor. Revenue streams likely include hosting, deployment services, and possibly premium MCP features. The absence of direct contact information and formal policies suggests an early-stage operation with potential growth in governance and compliance. Partnerships with cloud providers and analytics services support its ecosystem. The platform's growth indicators include a large number of MCP servers and active community engagement.

Security posture

Smithery.ai demonstrates a moderate security maturity level with HTTPS enforced and domain transfer protection enabled. However, the lack of DNSSEC and absence of published security policies or incident response contacts indicate gaps in security governance. No vulnerabilities or exposed sensitive data were identified in the analyzed content. The site does not implement advanced security headers, which could improve protection against common web attacks. Privacy compliance is weak due to missing privacy and cookie policies, which may expose the platform to regulatory risks under GDPR and similar frameworks. Incident response readiness is unclear, with no dedicated security contact channels found. Overall, the security posture is adequate for a startup but requires enhancements in policy transparency, DNS security, and security header implementation to meet best practices and regulatory expectations.

Recommendations

  1. Enable DNSSEC to enhance DNS security and prevent spoofing.
  2. Publish comprehensive privacy and cookie policies to improve GDPR compliance.
  3. Develop and display a security policy and incident response contact information.
  4. Implement standard security headers such as Content Security Policy (CSP), HSTS, and X-Frame-Options.
  5. Enhance transparency by providing clear business contact information and trust signals.
Site observations

Automated reading of the public site. Ratings are indicative.

Business

Description
Extend your agent's capabilities with Model Context Protocol servers. Integrate your AI with 5671 skills and extensions built by the community.
Key services
Model Context Protocol (MCP) server registry, AI agent skill and extension integration, Hosting and deployment of MCP servers, Documentation and playground for MCP usage
Content quality
good
Branding
consistent

Technology

Stack
Next.js, React, Cloudflare DNS, Supabase (storage for server icons), JavaScript, TypeScript (implied by MCP server descriptions)
Frameworks
Next.js
Platforms
Cloudflare, Supabase
Performance
fast
Mobile
good
Accessibility
basic
SEO
basic

Security

Observed score
75/100
Good practices seen
  • HTTPS enabled
  • Domain status clientTransferProhibited to prevent unauthorized transfers
  • Use of privacy protection for WHOIS

Analytics and tracking

Services
dubcdn.com analytics
Tracking level
minimal
Privacy practices
poor

Advertising

Tracking pixels
dubcdn.com analytics
Marketing tools
dubcdn.com analytics
Transparency
basic

Site quality

Design
good
User experience
good
Content relevance
good
Navigation
good
Professionalism
good
Trustworthiness
moderate

Key observations

  1. Website is a technology platform for AI agent integration via Model Context Protocol servers.
  2. Content is technical and developer-focused with detailed server listings and descriptions.
  3. No explicit privacy, cookie, or terms of service policies found on the main page.
  4. No direct contact emails or phone numbers visible in the content.
  5. Uses modern web technologies and hosting infrastructure.
  6. WHOIS data shows privacy protection and recent domain registration.
  7. No security policy or incident response information published.
  8. No signs of WAF or content blocking.
  9. Analytics script from dubcdn.com present, indicating some user tracking.
  10. No adult or questionable content detected.
Technical notes

Notes

The website is built on a modern technology stack featuring Next.js and React, ensuring a performant and responsive user experience. Hosting is managed via Cloudflare DNS and CDN services, with Supabase used for storage of media assets. The site loads quickly and is optimized for mobile devices, though accessibility features appear basic. SEO optimization is present but could be improved with richer metadata and structured data. The use of third-party analytics is minimal and does not appear intrusive. Technical debt is low given the recent domain registration and modern framework usage. Opportunities exist to enhance security configurations and privacy compliance to reduce technical risks and improve user trust.
Standards and sources

Reference chips under each finding point to the standard, regulation or specification the finding relates to. They are taken from the official datasets below and mapped conservatively: a finding with no defensible link shows none. NIS2 and GDPR references mark where a finding is relevant evidence, not a compliance verdict. Implementing Regulation (EU) 2024/2690 binds digital infrastructure and digital service providers; for other entities it is the most detailed public reading of the Article 21 measures. WCAG, EN 301 549, European Accessibility Act and Web Accessibility Directive references name the requirement an automated accessibility rule relates to; they are not a conformance verdict.

Retrieved 2026-10-25

Reviews of this site

Share your experience with smithery.ai. Every review is verified by email and published after moderation.

Overall rating
Select a rating
4000 characters remaining

We’ll email you to confirm your review and keep your details private.

Community rating

No published reviews yet. Be the first to review smithery.ai.

Feedback on this report

Rate this report, add an optional comment, and tell us if you want a security specialist to follow up.

Overall report quality
Select a rating
2000 characters remaining

We only use your feedback to improve Guard reports. Contact details are never shared.