Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

CybRelay

REMOTE · API.CYBRELAY.COM · 2 COMPONENTS

Vulnerability remediation for AI agents: deterministic fix scripts, AI advice only, web scan.

66 Trust /100

Last scanned (17 hours ago)

Scores higher than 51% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Security

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1185 tokens (~169/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
  • Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 7 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 20 Nov 26 +29
    • Authorization: fail → unverified ▼ security
    • Transport: unverified → pass ▲ security
    • Injection markers: unverified → pass ▲ security
    • First check of Judged manipulation: pass security
    • MCP protocol: unverified → pass ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • First check of Destructive annotations: pass functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: good functional
    • First check of Tool coverage: 100 functional
    • First check of Schema quality: fail functional
  • 17 Nov 26 36

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://api.cybrelay.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.cybrelay.com CN=WR3,O=Google Trust Services,C=US 18 Oct 2026 16 Jan 2027 RSA 2048 SHA256-RSA 174f68aac977aa81128e00360ae24904
SANs: api.cybrelay.com
CN=WR3,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7ff005a91568d63abc22861684aa4b5a
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.cybrelay.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
cybrelay.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self' https: data: blob:; script-src 'self' 'unsafe-inline' https://accounts.google.com https://accounts.google.com/gsi/client https://apis.google.com https://*.firebaseapp.com https://*.googleapis.com https://*.lemonsqueezy.com https://*.gstatic.com https://static.cloudflareinsights.com; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com https://accounts.google.com; img-src 'self' data: blob: https: https://*.googleusercontent.com https://avatars.githubusercontent.com https://*.gstatic.com; font-src 'self' data: https://fonts.gstatic.com; connect-src 'self' https: wss: https://*.googleapis.com https://*.firebaseio.com https://identitytoolkit.googleapis.com https://securetoken.googleapis.com https://*.lemonsqueezy.com https://accounts.google.com https://accounts.google.com/gsi/ https://cloudflareinsights.com; frame-src 'self' https://accounts.google.com https://*.firebaseapp.com https://*.lemonsqueezy.com; object-src 'none'; base-uri 'self'; form-action 'self' https://accounts.google.c
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.cybrelay.com/mcp Verified 200
http (plaintext) http://api.cybrelay.com/mcp HTTPS enforced 302 https://api.cybrelay.com/mcp
MCP tools · 7 exposed · ~1,185 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
analyze_file ~228

Analyse avec le moteur CybRelay le contenu envoyé par l'assistant : un fichier de code source ou le rapport d'un scanner (Trivy, SARIF, Snyk, SonarQube, Checkmarx, ZAP…). CybRelay ne clone aucun dépôt. Crédits débités selon le barème habituel ; un contenu déjà analysé n'est pas facturé une seconde fois.

NameTypeReqDescription
branchstring–Branche, pour ranger l’analyse dans le sous-projet correspondant
fail_onstring–Décision renvoyée (gate) : p1, p2 ou none (défaut)
file_contentstring–Contenu complet du fichier (15 Mo au plus)
file_namestring–Nom du fichier (ex. src/routes/user.ts ou trivy-report.json)
project_referencestring–Référence du projet CybRelay (PRJ-…) où ranger l’analyse
repo_urlstring–Adresse du dépôt, pour ranger l'analyse dans le projet correspondant (aucun clonage)

No output schema declared.

No examples provided.

apply_remediation_patch ~166

[Ancien nom gardé pour compatibilité : utilisez get_remediation_patch] Fournit le script de correction d'une faille de votre espace (et le correctif .patch quand le moteur a pu le valider sur le fichier envoyé). CybRelay n'applique rien dans votre dépôt et n'ouvre aucune pull request : l'assistant ou vous l'appliquez après relecture.

NameTypeReqDescription
file_contentstring–Contenu actuel du fichier concerné (2 Mo au plus) : permet au moteur de préparer et valider un correctif .patch
languagestring–Langage du script de correction (bash par défaut)
vulnerability_idstringyesIdentifiant exact de la faille (renvoyé par list_vulnerabilities)

No output schema declared.

No examples provided.

get_remediation_patch ~150

Fournit le script de correction d'une faille de votre espace (et le correctif .patch quand le moteur a pu le valider sur le fichier envoyé). CybRelay n'applique rien dans votre dépôt et n'ouvre aucune pull request : l'assistant ou vous l'appliquez après relecture.

NameTypeReqDescription
file_contentstring–Contenu actuel du fichier concerné (2 Mo au plus) : permet au moteur de préparer et valider un correctif .patch
languagestring–Langage du script de correction (bash par défaut)
vulnerability_idstringyesIdentifiant exact de la faille (renvoyé par list_vulnerabilities)

No output schema declared.

No examples provided.

get_scan_status ~67

Donne l'état et la synthèse (sévérités, priorités, empreinte SHA-256 du fichier analysé) d'une analyse de votre espace.

NameTypeReqDescription
scan_job_idstringyesIdentifiant de l'analyse renvoyé par trigger_pipeline_scan (analysis_id)

No output schema declared.

No examples provided.

list_vulnerabilities ~194

Liste les failles réellement enregistrées dans votre espace CybRelay (analyses du site, du pipeline CI, de l'API et de la passerelle MCP), triées par priorité. Filtres stricts : un filtre sans correspondance renvoie 0 résultat.

NameTypeReqDescription
analysis_idstring–Identifiant d'une analyse (renvoyé par trigger_pipeline_scan)
deduplicated_onlyboolean–Une faille retrouvée dans plusieurs analyses ne compte qu’une fois (la plus récente)
limitinteger–Nombre maximum de résultats (100 au plus)
prioritystring–Filtre par priorité CybRelay
repo_namestring–Projet : référence PRJ-…, nom du projet, adresse du dépôt ou « organisation/dépôt ». Vide ou « all » : tout l'espace.
severitystring–Filtre par sévérité

No output schema declared.

No examples provided.

scan_url_surface ~137

Scan SURFACE d'un site : contrôles passifs de configuration (en-têtes HTTP, TLS, redirection HTTPS, cookies, DNS de messagerie, security.txt), note de A+ à F. Aucun test d'intrusion. 1 scan gratuit par jour pour l'espace, ensuite payé en crédits au prix de la page publique. Résultat lisible 48 h ; masqué de la liste publique sauf hidden=false.

NameTypeReqDescription
hiddenboolean–true (par défaut) : absent de la liste publique des scans récents
urlstringyesAdresse du site (ex. https://exemple.com)

No output schema declared.

No examples provided.

trigger_pipeline_scan ~243

[Ancien nom gardé pour compatibilité : utilisez analyze_file] Analyse avec le moteur CybRelay le contenu envoyé par l'assistant : un fichier de code source ou le rapport d'un scanner (Trivy, SARIF, Snyk, SonarQube, Checkmarx, ZAP…). CybRelay ne clone aucun dépôt. Crédits débités selon le barème habituel ; un contenu déjà analysé n'est pas facturé une seconde fois.

NameTypeReqDescription
branchstring–Branche, pour ranger l’analyse dans le sous-projet correspondant
fail_onstring–Décision renvoyée (gate) : p1, p2 ou none (défaut)
file_contentstring–Contenu complet du fichier (15 Mo au plus)
file_namestring–Nom du fichier (ex. src/routes/user.ts ou trivy-report.json)
project_referencestring–Référence du projet CybRelay (PRJ-…) où ranger l’analyse
repo_urlstring–Adresse du dépôt, pour ranger l'analyse dans le projet correspondant (aucun clonage)

No output schema declared.

No examples provided.

Install

How do I install the CybRelay MCP server?

CybRelay is a hosted endpoint at https://api.cybrelay.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.cybrelay.com

# add to Claude Code
claude mcp add --transport http com-cybrelay-mcp 'https://api.cybrelay.com/mcp'
Common questions

What is the CybRelay MCP server?

CybRelay is an MCP server listed in the public MCP registry as com.cybrelay/mcp. Vulnerability remediation for AI agents: deterministic fix scripts, AI advice only, web scan. This page covers its hosted endpoint (https://api.cybrelay.com/mcp).

Is the CybRelay MCP server safe to use?

CybRelay scores 66 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the CybRelay MCP server expose?

CybRelay exposes 7 tools: list_vulnerabilities, analyze_file, trigger_pipeline_scan, get_remediation_patch, apply_remediation_patch, and 2 more. Their descriptions and schemas cost roughly 1,185 tokens of context every time the server is loaded.

Does the CybRelay MCP server require authentication?

No. We connected to CybRelay without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the CybRelay MCP server still maintained?

CybRelay is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the CybRelay MCP server?

VerifyMCP ran 12 checks on CybRelay, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about CybRelay: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.