Scans GitHub repositories and MCP skills for security vulnerabilities including prompt injection attacks, malware, and OWASP top ten risks. Exposes three main operations: get_report for detailed vulnerability analysis, check_certification to verify safety compliance status, and scan_skill for evaluating external dependencies. You'd reach for this when auditing codebases or third-party integrations before deployment, especially if you're concerned about AI-specific attack vectors like prompt injection that traditional security scanners miss. Requires an API key from apisecurityscan.net. Running over HTTP with solid uptime at 99.9% and median latency around 724ms based on real usage data.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent