loading…
Spring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
автор: Community
0.00
Search for a command to run...
loading…
Provides three AI security tools for Claude: scanning MCP servers for security risks, validating HDP delegation chains against IETF standards, and triaging secu
Provides three AI security tools for Claude: scanning MCP servers for security risks, validating HDP delegation chains against IETF standards, and triaging security alerts with kill-chain analysis.
Agentic-AI security tools for Claude, exposed as a remote MCP server and listed in the Claude Connectors Directory.
| Tool | What it does |
|---|---|
helixar_inspect_mcp |
Scan an MCP server (URL or raw manifest JSON) against Sentinel detection rules. Returns risk score, findings, and a Claude-generated security brief. Quick mode is free + authless (top 8 rules). Deep mode runs all 26 rules with an API key. |
helixar_hdp_validate |
Validate an HDP delegation chain against IETF draft draft-helixar-hdp-agentic-delegation-00. Surfaces scope escalations, depth violations, expired hops, missing signatures. Every output cites the IETF draft + Zenodo DOI. |
helixar_releaseguard |
Wraps Helixar-AI/ReleaseGuard. Quick mode scans dist/ / release artifacts for secrets, metadata leaks, license gaps. Deep mode runs the full harden pipeline (fix + obfuscate + sign + attest). Requires the releaseguard binary on PATH. |
npm install
npm test
npm run build
npm start # stdio MCP server
The hosted server lives at https://mcp.helixar.ai. To use it before Anthropic lists it in the directory:
https://mcp.helixar.aiFor local development, point Claude Desktop at node /path/to/helixar-mcp/dist/server.js as a stdio server.
@modelcontextprotocol/sdk (official Anthropic)src/worker.ts, deployed to mcp.helixar.ai)| Mode | Auth | Tools / scope | Purpose |
|---|---|---|---|
| Quick / public | none | inspect_mcp (top-8 rules), hdp_validate, releaseguard check |
Maximum reach — zero-friction for community adoption |
| Authenticated | API key (OAuth2) | inspect_mcp deep mode (26 rules), releaseguard fix/harden/sbom |
Pilot customers + paid tier |
src/
├── server.ts # MCP stdio entrypoint
├── worker.ts # Cloudflare Workers HTTP adapter (Phase 7)
├── lib/
│ ├── narrate.ts # Anthropic call + deterministic fallback
│ ├── sentinel-rules.ts # 26 Sentinel detection rules (top-8 quick + 18 deep)
│ ├── hdp-schema.ts # HDP chain types + 9 validation rules
│ └── releaseguard-runner.ts # CLI adapter for the releaseguard binary
└── tools/
├── inspect-mcp.ts # helixar_inspect_mcp implementation
├── hdp-validate.ts # helixar_hdp_validate implementation
└── releaseguard.ts # helixar_releaseguard implementation
tests/
└── (mirrors src/)
Per the implementation plan §6, internal detection methodology, Hunch Mode internals, sensor implementation, and exact thresholds are never exposed in this codebase. Public surface is rule IDs, severity buckets, public-safe detection categories, and remediation guidance only. The earlier helixar_triage_alert tool was revoked in v0.4.1 after review flagged that exposing kill-chain stage classifiers — even stripped — widened the public attack surface too far; helixar_releaseguard (wrapping the already-open-source Helixar-AI/ReleaseGuard) replaces it.
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"helixar-security-mcp-server": {
"command": "npx",
"args": []
}
}
}