MCPskills
Related Servers
Alternatives to MCPskills
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceScans MCP servers for prompt injection, supply chain attacks, excessive permissions, and code execution risks. Includes an offline blacklist that catches known-compromised packages like LiteLLM 1.82.7/1.82.8 and Trivy with zero latency.19MIT
- AlicenseAqualityBmaintenanceTrust-scan gate for MCP servers: evidence-backed verdicts before you install.6MIT
- AlicenseNot gradedqualityBmaintenanceScans MCP servers, AI agent skills, and plugins for 68+ malicious patterns including credential exfiltration, prompt injection, and code execution.49 npm6MIT
- AlicenseNot gradedqualityDmaintenanceScans MCP servers for security vulnerabilities, prompt injection, and tool poisoning, providing risk scores and protection.4MIT
- AlicenseNot gradedqualityAmaintenanceScans MCP servers and AI tools for security risks, providing 4-dimensional scoring and badges, with optional guardrail MCP for auto-protection.2MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that scans PyPI packages and GitHub repos for security vulnerabilities, dangerous patterns, and prompt injection vectors, providing trust scores (0-10) and side-by-side comparisons.MIT
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: auto_gate gives a simple go/no-go decision, check_trust_score provides detailed scoring, batch_check handles multiples, scan_safety focuses on safety, list_packages curates packages, build_stack recommends stacks, get_badge generates badges, check_watched and watch_repo monitor changes. No two tools have overlapping functionality that would cause confusion.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., auto_gate, batch_check, check_trust_score, watch_repo). The naming is predictable and easy to parse, with no mixing of conventions.
With 9 tools, the set is well-scoped for a trust and safety assessment server. Each tool serves a necessary function without being redundant or excessive, fitting comfortably within the ideal 3-15 range.
The tool surface covers the full lifecycle of trust assessment: single and batch scoring, safety scanning, recommendation (build_stack), curated packages (list_packages), monitoring (watch_repo, check_watched), and a badge output (get_badge). There are no obvious gaps for the stated purpose.