This MCP server exposes Helixar's agentic AI security tools directly in Claude and other MCP-compatible clients. It provides three tools: scanning MCP servers against Sentinel detection rules for risk assessment, validating agentic delegation chains per IETF draft standards, and wrapping the ReleaseGuard tool to scan release artifacts for secrets and license gaps. The server is deployed on Cloudflare Workers and supports both remote HTTP and local stdio operation.
Cognium trust score
61%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-01.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.