Skip to content
MCP server

CybRelay

MCP server giving AI coding agents vulnerability scans and deterministic fix scripts

Install
Pricing
Freemium
Platforms
API, CLI, vscode
Runs
Remotely
Version
1.1.0
Listing updated
today

About CybRelay

CybRelay is a freemium MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.

The README describes CybRelay's remote MCP server as the way an AI agent reaches the CybRelay platform. Through it, an agent can send source files or existing scanner reports (SARIF, Trivy, Snyk and others) for analysis, list the findings stored in a workspace, request a remediation script for a finding, and run a passive configuration check on a website. Access uses a workspace API key sent as a bearer header, and usage is billed in credits.

The fixes are generated by a rules and syntax-analysis engine rather than by a language model. The AI model is only used to add advisory comments to scripts. When a fix cannot be validated, the server returns a written remediation guide instead of a patch, and the server itself does not apply changes to a repository. The README also says that scripts are dry-run first and that tests are run with automatic rollback when they fail.

The server is aimed at developers and security teams who work with AI assistants such as Claude Code, Cursor, Windsurf and VS Code and want findings reviewed before code changes are made. The website describes a French-language, Morocco-based B2B SaaS company, and the README states that analysis is hosted in the EU.

Install

Run in a terminal

claude mcp add --transport http mcp https://api.cybrelay.com/mcp

Add to Settings → Connectors → Add custom connector

https://api.cybrelay.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.cybrelay.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://api.cybrelay.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://api.cybrelay.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://api.cybrelay.com/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (5)

Taken from the project documentation; the running server may differ.

scan_url_surface
Passive configuration scan of a website for HTTP headers, TLS, cookies, mail DNS and security.txt.
analyze_file
Analyses a source file or scanner report sent by the agent.
list_vulnerabilities
Lists findings stored in the workspace, sorted by priority.
get_scan_status
Returns status and summary of an analysis.
get_remediation_patch
Returns a remediation script for a finding, and a validated patch when the current file is sent.

What it does

Deterministic fix scripts
Remediation scripts come from a rules and syntax engine, so the same input yields the same script, with AI limited to advisory comments.
Scanner report import
Accepts SARIF, Trivy, Snyk, SonarQube, Checkmarx, OWASP ZAP and Nessus reports, then removes duplicates and ranks findings P1 to P4.
Passive website scan
Checks HTTP security headers, TLS, HTTPS redirects, cookies, mail DNS and security.txt, returning a grade from A+ to F.
Validated patch output
A .patch file is returned only when it has been applied in memory, syntax-checked and shown to neutralise the vulnerability.
Workspace findings listing
Lists stored findings filtered by project, analysis, severity or priority.
Streamable HTTP and SSE
Offers a streamable HTTP endpoint and a legacy SSE endpoint, with a documented client configuration for several AI coding tools.

Good for

  • Triage critical findings from a Trivy or Snyk report inside an AI coding assistant
  • Get a fix script for a specific file flagged by static analysis before committing
  • Run a quick passive header and TLS check on a website from within an agent session
  • Review remediation steps for security findings without letting an AI push changes to a repository

Pricing

Freemium

Free plan with 50 one-time credits; Starter €39/month, Pro €99/month, Enterprise by quote.

Prices change. Check cybrelay.com before you buy.

CybRelay FAQ

Does the server change my repository?

The README says CybRelay never connects to, clones or writes to a repository. The get_remediation_patch tool applies nothing, and the user or agent reviews and applies changes.

How is the server authenticated?

Requests send an Authorization header with a Bearer token, which is a CybRelay workspace API key generated in the account settings.

What does a free account include?

The README lists a free plan with 50 credits valid for one month, and one free website scan per day per workspace.

Which endpoints are available?

The README lists https://api.cybrelay.com/mcp for streamable HTTP (recommended) and https://api.cybrelay.com/sse for legacy SSE.

Is CybRelay free?

CybRelay has a free plan, with paid plans for more usage or features.

How do I add CybRelay to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://api.cybrelay.com/mcp

What are the best alternatives to CybRelay?

The closest alternatives to CybRelay are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Where this comes from

  • Description: written from the project's README, the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers

Alternatives to CybRelay

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 467K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.8K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    • Remote
    • Open source
    • 34.6K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools