MCPサーバー

ScanLabsAI Security Scanner

            com.scanlabsai/scanner
        

開発者向けツールセキュリティ公開・接続可能 MCP 2026-07-28

このMCPでできること

Scans websites and AI agents for vulnerabilities, compliance issues, CVEs, configuration weaknesses, and remediation guidance.

buy_credits

Get a secure Stripe checkout link to buy an AI credit pack for the signed-in account. Requires a ScanLabsAI API key in the MCP connection. Credits are added automatically once payment completes. Packs: starter (5), pro (15), agency (50).

入力スキーマ

{'type': 'object', 'properties': {'pack': {'type': 'string', 'description': 'Pack id: starter, pro, or agency. Defaults to pro.'}}}

check_credits

Check the signed-in account's AI credit balance. Requires a ScanLabsAI API key in the MCP connection (Authorization: Bearer slai_...). Create one at https://scanlabsai.com/mcp.

入力スキーマ

{'type': 'object', 'properties': {}}

compliance_report

Generate a website compliance report — the same automated assessment the ScanLabsAI agency portal runs — covering GDPR/CCPA privacy, WCAG 2.1 AA accessibility, PCI DSS 4.0 payment security and general standards. Returns an overall score, per-category scores and the failing/at-risk checks with recommendations, as Markdown. Requires a ScanLabsAI API key in the connection; costs 1 AI credit per report. Only run against sites you are authorised to assess.

入力スキーマ

{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The website URL to assess for compliance, e.g. https://example.com'}}}

get_fix_guidance

Get detailed, step-by-step remediation guidance for a specific vulnerability or security issue (e.g. "missing Content-Security-Policy header", "SQL injection", a CVE id). Returns actionable fixes.

入力スキーマ

{'type': 'object', 'required': ['issue'], 'properties': {'issue': {'type': 'string', 'description': 'The vulnerability, finding title, or CVE id to fix.'}}}

get_pricing

Get ScanLabsAI pricing: the free-first-scan policy and AI credit packs.

入力スキーマ

{'type': 'object', 'properties': {}}

lookup_cves

Look up recent CVEs from the NIST NVD feed, optionally filtered by keyword. Returns id, severity, score and summary.

入力スキーマ

{'type': 'object', 'properties': {'limit': {'type': 'number', 'description': 'Max results (1-25). Defaults to 10.'}, 'keyword': {'type': 'string', 'description': 'Optional keyword, e.g. "wordpress" or "openssl".'}}}

scan_agent

Red-team an AI agent for security weaknesses — prompt injection, system-prompt leakage, sensitive-data disclosure, unsafe output handling and excessive agency — mapped to the OWASP LLM Top 10, and return a Markdown report. This is agent-to-agent scanning: use it to assess another agent from here. Two target kinds are supported: kind="openai" for an OpenAI-compatible chat-completions endpoint, or kind="mcp" for an MCP server (its tool manifest is audited for tool-poisoning and over-broad capabilities). Requires a ScanLabsAI API key in the connection; each agent scan uses 5 AI credits. Probing is active and adversarial — only scan agents you own or are authorised to test.

入力スキーマ

{'type': 'object', 'required': ['kind', 'endpoint'], 'properties': {'deep': {'type': 'boolean', 'description': 'Run deeper probes (jailbreak + resource-exhaustion). Defaults to false.'}, 'kind': {'enum': ['openai', 'mcp'], 'type': 'string', 'description': 'Target type: "openai" for a chat-completions endpoint, "mcp" for an MCP server.'}, 'model': {'type': 'string', 'description': 'Model name for OpenAI-compatible endpoints, e.g. gpt-4o-mini.'}, 'apiKey': {'type': 'string', 'description': 'Optional bearer token / API key the target agent requires. Sent to the target only; not stored.'}, 'endpoint': {'type': 'string', 'description': 'The agent endpoint URL (chat-completions URL, or MCP server URL).'}}}

scan_website

Run a ScanLabsAI security scan against a website and return a full Markdown vulnerability report (grouped by severity, with descriptions and remediation) that you can analyse, act on, and the user can save as security-report.md. Checks OWASP Top 10, CVEs, SSL/TLS, security headers and DNS. Use deep=true for a comprehensive scan (40,000+ vectors, slower). Only scan sites the user is authorised to test.

入力スキーマ

{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The website URL to scan, e.g. https://example.com'}, 'deep': {'type': 'boolean', 'description': 'Run a deep scan (comprehensive, slower). Defaults to false.'}}}

追加

                            buy_credits
                        

2026年9月17日12:37

追加

                            check_credits
                        

2026年9月17日12:37

追加

                            get_pricing
                        

2026年9月17日12:37

追加

                            lookup_cves
                        

2026年9月17日12:37

追加

                            get_fix_guidance
                        

2026年9月17日12:37

追加

                            compliance_report
                        

2026年9月17日12:37

追加

                            scan_agent
                        

2026年9月17日12:37

追加

                            scan_website
                        

2026年9月17日12:37

サーバー情報

バージョン

1.1.0

通信方式

Streamable HTTP

ツール

レイテンシ

501 ms

最終スキャン

2026年10月1日2:54

初回確認

2026年9月13日2:13

エンドポイント

https://scanlabsai.com/api/mcp

ScanLabsAI Security Scanner

このMCPでできること

ツール

最近のツール変更

類似のMCPサーバー

hyperion

Vee3

IA-QA — 130+ QA & Dev Tools for AI Agents

validoria-mcp

HubVibe: Pay-per-Call Tools for AI Agents: Web Search, Email Verify, KYC, Stocks, Crypto, News, Data

developer-tools

Qiniso

ContrastAPI