Raw scan report

Bicameral — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.

← Back to the scan page
{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.13.0",
    "methodologyVersion": "mcptrustchecker-1.13"
  },
  "target": {
    "id": "bicameral-mcp",
    "source": {
      "kind": "package",
      "origin": "bicameral-mcp"
    },
    "server": {
      "name": "bicameral-mcp"
    }
  },
  "grade": "A",
  "score": {
    "score": 92,
    "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": "high",
        "label": "capability blast radius (high) — client exposure if the model is manipulated",
        "appliedPenalty": 6
      },
      {
        "kind": "client",
        "term": "verification-discount",
        "level": "none",
        "label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
        "appliedPenalty": 2
      },
      {
        "kind": "client",
        "term": "coverage-honesty",
        "level": "source",
        "label": "inspection depth (source) — how much of the target the scan could see",
        "appliedPenalty": 0
      }
    ],
    "gatesFired": [],
    "methodologyVersion": "mcptrustchecker-1.13"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "can execute shell commands or code"
    ],
    "tags": [
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (32 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
    ]
  },
  "findings": [
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (preflight_adapters/base.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`preflight_adapters/base.py:792`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "preflight_adapters/base.py"
      },
      "evidence": "branch = ( subprocess.check_output( [\"git\", \"rev-parse\", \"--abbrev-ref\", \"HEAD\"],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "preflight_adapters/base.py",
        "line": 792,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (preflight_adapters/state.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`preflight_adapters/state.py:47`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "preflight_adapters/state.py"
      },
      "evidence": "ry: completed = subprocess.run( [\"ps\", \"-o\", \"ppid=\", \"-p\", str(pid)], check=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "preflight_adapters/state.py",
        "line": 47,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tool_request.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tool_request.py:415`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "tool_request.py"
      },
      "evidence": "url = ( subprocess.check_output( [\"git\", \"config\", \"--get\", \"remote.origin.url\"],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tool_request.py",
        "line": 415,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SUP-011",
      "title": "Package declares no source repository",
      "category": "supply-chain",
      "severity": "info",
      "confidence": "strong",
      "description": "\"bicameral-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
      "remediation": "Prefer packages that link to public, reviewable source.",
      "location": {
        "kind": "package",
        "name": "bicameral-mcp"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "bicameral.product.select",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.ingest",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.capture_context",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.preflight",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.lookup",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.context",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.correction_findings",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.bind",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.workspace.bind",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.binding.inspect",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.evidence.refresh",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.corpus_proposals",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.accept_candidate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.reject_candidate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.promote_candidate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.request_corpus_change",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.approve_signoff",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.reject_signoff",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.resolve_compliance",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.brief",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.history",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.recall.inspect_evidence",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.recall.expand_scope",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.contradictions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.review.triage_contradiction",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.governance.inbox",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.governance.inspect",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.governance.resolve",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.privacy.erase_subject.approve",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.privacy.erase_subject",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.request_correction.approve",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bicameral.request_correction",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "569f9526f977d8861d1cb71e48654a6d4fe67e6fb208553284ff37368c8767d8",
  "stats": {
    "tools": 32,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 3,
      "medium": 0,
      "low": 0,
      "info": 1
    }
  }
}