Vulnerability Scanner

io.github.GuardBeePublished by GitHub account GuardBeev0.4.1Updated Nov 3, 2026

Triggers GuardBee scans, queries findings, AI-assisted remediation guidance

Overview

AI-generated overview

Runs GuardBee security scans on URLs from an AI assistant and returns vulnerability findings with remediation guidance.

What you can do
  • Start a GuardBee scan on a URL or brand ID, optionally waiting for completion
  • Check scan status and summary counts by scan ID
  • List recent workspace scans with filters
  • Retrieve findings filtered by severity, scan ID or brand ID, each with title, description and remediation advice
  • Run a full scan and immediately return critical and high findings with fix guidance
When to use it
Useful when you want an assistant to run OWASP-style security checks on a site, summarize critical and high findings, and suggest fixes, including KVKK, GDPR or CCPA-focused compliance scans.
Requirements
Runs locally over stdio via the npm package, typically launched with npx. Requires a GuardBee API key in the GUARDBEE_API_KEY environment variable; an optional GUARDBEE_BASE_URL overrides the default endpoint. Network access to the GuardBee service is needed.
Before you install
The API key is a credential passed in the environment. Scans are started against live URLs and consume GuardBee workspace resources. Optional telemetry, enabled with GUARDBEE_TELEMETRY=1, sends server, tool, success, duration and short parameter values such as file paths to a telemetry package, with longer strings and fields like content, token or password replaced by a placeholder.

Installation

In SourceWeft

  1. Open Vulnerability Scanner in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@guardbee/mcp-vulnerability-scanner

🇬🇧 English | 🇹🇷 Türkçe | 🇨🇳 中文 | 🇯🇵 日本語 | 🇰🇷 한국어 | 🇧🇷 Português | 🇪🇸 Español | 🇩🇪 Deutsch

[npm version] [npm downloads] [License: MIT]

Trigger a GuardBee security scan directly from a Claude conversation. Run OWASP checks, query findings, and have the AI prioritize remediation recommendations.

Telemetry is off by default. With GUARDBEE_TELEMETRY=1 it sends the server, tool, success, duration and short parameter values such as a file path; longer strings and fields like content, token or password are replaced with a placeholder. See @guardbee/mcp-telemetry.

A GuardBee API key is required. Get one at app.guardbee.ai/developers.


Features

  • Trigger a Scan from Claude — start a GuardBee scan on any URL with one command
  • Status Queries — check scan progress and summary counts in real time
  • Finding Filters — query by severity, scan ID, or brand ID
  • Remediation Guidance — an explanation and an actionable recommendation for every finding
  • Scan Scenarios — quick, kvkkFocus, gdprFocus, ccpaFocus
  • 36 Scan Modules — all of GuardBee's modules are supported
  • 25 Unit Tests — a test suite that doesn't require API calls

Quick Start

bash
npm install -g @guardbee/mcp-vulnerability-scanner

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "guardbee-vulnerability-scanner": {      "command": "npx",      "args": ["-y", "@guardbee/mcp-vulnerability-scanner"],      "env": {        "GUARDBEE_API_KEY": "gb_..."      }    }  }}

Get your API key at app.guardbee.ai/developers.


MCP Tools

ToolDescription
start_scanStarts a scan for a URL or brand ID; with wait=true waits for completion
get_scan_statusLive status and summary counts by scan ID
list_scansLists workspace scans with filters
get_findingsFetches findings filtered by severity / scanId / brandId
scan_and_reportScan + wait + return critical/high findings and remediation recommendations

Example Usage

You can ask Claude:

"Scan https://example.com and give me a security report"

"List my recent scans"

"Show critical findings for scan clz001 and explain how to fix them"

"Run a KVKK-focused scan on example.com"

Example Output

⚠️  Security scan complete for https://example.com   Scan ID  : clz001abc   🔴 Critical : 2   🟠 High     : 5   🟡 Medium   : 8   🔵 Low      : 3   ⚪ Info     : 12   ✅ Passed   : 18
Use get_findings with scanId="clz001abc" to see details and remediation steps.

Scan Scenarios

ScenarioDescription
quickAll 36 modules — comprehensive general scan
kvkkFocusFocused on KVKK compliance modules
gdprFocusFocused on GDPR compliance modules
ccpaFocusFocused on CCPA compliance modules

Environment Variables

VariableDescription
GUARDBEE_API_KEYGuardBee API key (required)
GUARDBEE_BASE_URLCustom endpoint (default: https://app.guardbee.ai)

Development

bash
npm installnpm test          # 25 unit testsnpm run build     # TypeScript compile

License

MIT — GuardBee

Feedback

Questions, ideas, or a false positive? Start a thread in GitHub Discussions or open an issue. If GuardBee is useful to you, a ⭐ on the repository helps others find it.

Source: packages/vulnerability-scanner/README.md at commit bc5997d

Tools

5

start_scan

Start a GuardBee security scan on a URL. Returns a scan ID you can use to check status and get findings.

ParametersurlwaitbrandIdscenario

get_scan_status

Get the current status and summary of a GuardBee scan by ID

ParametersscanIdrequired

list_scans

List recent GuardBee scans in your workspace

ParameterspagestatusbrandIdpageSize

get_findings

Get vulnerability findings from a GuardBee scan with optional severity filter. Includes title, description, and remediation recommendation per finding.

ParameterspagescanIdbrandIdpageSizeseverity

scan_and_report

Run a full GuardBee scan and immediately return all critical and high findings with remediation guidance. Best for quick security assessments.

Parametersurlrequiredscenario

Version history

3
  1. v0.4.1LatestOct 30, 2026
  2. v0.3.2Oct 22, 2026
  3. v0.2.5Oct 13, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts