Security MCP servers
Scanners, advisory feeds, and analysis tools an agent can drive. Security work is checklist-heavy, and agents are relentless about checklists. Ironically, this is also the category where you should read the permissions panel twice.
What engineers use them for
- Scan dependencies and summarize what's actually exploitable
- Watch advisories relevant to your stack
- Audit configurations against a baseline
- Draft the remediation ticket with evidence attached
Highest-graded right now
Graded on maintenance, completeness, and reliability. The formula is public →squirrelscan
Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.
Virustotal
MCP server for querying VirusTotal API with comprehensive security analysis tools.
Agent Security Scanner
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
GitHits
Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Notebooklm Secure
Security-hardened NotebookLM MCP with post-quantum encryption
mcp
Easily find and fix security issues in your applications leveraging Snyk platform capabilities.
Spotdb
Ephemeral data sandbox for AI workflows with guardrails and security