Raw scan report

GEIANT — Geospatial AI Governance Runtime — the complete, unedited output of the deterministic mcptrustchecker engine v1.10.0, scanned 2026-07-24. Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.

{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.10.0",
    "methodologyVersion": "mcptrustchecker-1.9"
  },
  "target": {
    "id": "https://packagesmcp-perception-production.up.railway.app/sse",
    "source": {
      "kind": "http",
      "origin": "https://packagesmcp-perception-production.up.railway.app/sse"
    },
    "server": {
      "name": "geiant-perception",
      "version": "0.3.0"
    }
  },
  "grade": "A",
  "score": {
    "score": 97,
    "threatScore": 100,
    "grade": "A",
    "band": "A",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "client",
        "term": "capability-exposure",
        "level": "moderate",
        "label": "capability blast radius (moderate) — client exposure if the model is manipulated",
        "appliedPenalty": 3
      },
      {
        "kind": "client",
        "term": "coverage-honesty",
        "level": "live",
        "label": "inspection depth (live) — how much of the target the scan could see",
        "appliedPenalty": 0
      }
    ],
    "gatesFired": [],
    "methodologyVersion": "mcptrustchecker-1.9"
  },
  "capability": {
    "level": "moderate",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)"
    ],
    "tags": [
      "untrusted-input"
    ]
  },
  "coverage": {
    "level": "live",
    "inputs": {
      "toolSurface": true,
      "implementationSource": false,
      "packageMetadata": false,
      "liveTransport": true
    },
    "caveats": []
  },
  "findings": [
    {
      "ruleId": "MTC-NET-005",
      "title": "Remote HTTP MCP endpoint",
      "category": "network",
      "severity": "info",
      "confidence": "strong",
      "description": "Remote endpoint packagesmcp-perception-production.up.railway.app. MCP Trust Checker does not test server-side authentication/authorization; verify the endpoint requires auth.",
      "location": {
        "kind": "transport"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "perception_fetch_tile",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "perception_classify",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "perception_embed",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "perception_weather",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "gns_get_trust_score",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "gns_verify_chain",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "gns_roll_epoch",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "gns_get_compliance_report",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "d57d34c786ed52f9e3b0252f3d4ceb882a9847734f9eff98fbe429f4bcf72895",
  "stats": {
    "tools": 8,
    "prompts": 0,
    "resources": 1,
    "findingsBySeverity": {
      "critical": 0,
      "high": 0,
      "medium": 0,
      "low": 0,
      "info": 1
    }
  }
}