Nucleus — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "nucleus-mcp",
"source": {
"kind": "package",
"origin": "nucleus-mcp"
},
"server": {
"name": "nucleus-mcp"
}
},
"grade": "A",
"score": {
"score": 93,
"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": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"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-1.8"
},
"capability": {
"level": "high",
"reasons": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (11 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-006",
"title": "Reads a sensitive credential path or dumps the environment (src/mcp_server_nucleus/cli.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/cli.py:831`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "src/mcp_server_nucleus/cli.py"
},
"evidence": "ssh\", \".aws\", \".gnupg\", \".config/gcloud\", \"id_rsa\", \"id_ed25519\", \"id_dsa\", \"id_ecdsa\", \"stripe_live\", \"",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "src/mcp_server_nucleus/cli.py",
"line": 831,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/admin/switch_brain.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/admin/switch_brain.py:82`): 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": "src/mcp_server_nucleus/admin/switch_brain.py"
},
"evidence": "s...\") try: subprocess.run( [\"pkill\", \"-f\", _NUCLEUS_PROCESS_PATTERN], check=False, timeout=5",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/admin/switch_brain.py",
"line": 82,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/cli.py:390`): 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": "src/mcp_server_nucleus/cli.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"log\", \"--oneline\", \"-100\"], cwd=repo_root,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/cli.py",
"line": 390,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/commitment_core.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/commitment_core.py:32`): 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": "src/mcp_server_nucleus/commitment_core.py"
},
"evidence": "y: result = subprocess.run( [\"rg\", r\"- \\[ \\]\", str(artifacts_path), \"--type\", \"md\", \"-n\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/commitment_core.py",
"line": 32,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/commitment_ledger.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/commitment_ledger.py:942`): 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": "src/mcp_server_nucleus/commitment_ledger.py"
},
"evidence": "try: result = subprocess.run( [\"rg\", \"--type\", \"md\", \"-n\", \"--no-heading\", \"--glob\", \"!*.resolved.",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/commitment_ledger.py",
"line": 942,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/core/egress_proxy.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/core/egress_proxy.py:77`): 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": "src/mcp_server_nucleus/core/egress_proxy.py"
},
"evidence": "rt sys result = subprocess.run( [sys.executable, \"-m\", \"pip\", \"install\", package], captu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/core/egress_proxy.py",
"line": 77,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/flywheel/core.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/flywheel/core.py:211`): 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": "src/mcp_server_nucleus/flywheel/core.py"
},
"evidence": "try: proc = subprocess.run( [ \"gh\", \"issue\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/flywheel/core.py",
"line": 211,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/hypervisor/locker.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/hypervisor/locker.py:22`): 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": "src/mcp_server_nucleus/hypervisor/locker.py"
},
"evidence": "y: result = subprocess.run( cmd, capture_output=True, text",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/hypervisor/locker.py",
"line": 22,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/runtime/agent_os/verified_record.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/runtime/agent_os/verified_record.py:36`): 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": "src/mcp_server_nucleus/runtime/agent_os/verified_record.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"--show-toplevel\"], capture_output=",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/runtime/agent_os/verified_record.py",
"line": 36,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/runtime/auto_awake.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/runtime/auto_awake.py:251`): 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": "src/mcp_server_nucleus/runtime/auto_awake.py"
},
"evidence": "ion\"] = True proc = subprocess.Popen(cmd, **kwargs) # type: ignore[arg-type] try: if proc.stdin is not",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/runtime/auto_awake.py",
"line": 251,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/mcp_server_nucleus/runtime/capabilities/code_ops.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_server_nucleus/runtime/capabilities/code_ops.py:181`): 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": "src/mcp_server_nucleus/runtime/capabilities/code_ops.py"
},
"evidence": "result = subprocess.run( cmd_parts, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/mcp_server_nucleus/runtime/capabilities/code_ops.py",
"line": 181,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (src/mcp_server_nucleus/cli.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`src/mcp_server_nucleus/cli.py:8005`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "src/mcp_server_nucleus/cli.py"
},
"evidence": "try: __import__(mod_name) _pass(label) except ImportError: _fail(labe",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "src/mcp_server_nucleus/cli.py",
"line": 8005,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"nucleus-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "nucleus-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "nucleus_relay_subscribe",
"tags": [],
"reasons": {}
},
{
"tool": "nucleus_search",
"tags": [],
"reasons": {}
},
{
"tool": "depth_push",
"tags": [],
"reasons": {}
},
{
"tool": "depth_pop",
"tags": [],
"reasons": {}
},
{
"tool": "depth_show",
"tags": [],
"reasons": {}
},
{
"tool": "depth_map",
"tags": [],
"reasons": {}
},
{
"tool": "switch_context",
"tags": [],
"reasons": {}
},
{
"tool": "add_loop",
"tags": [],
"reasons": {}
},
{
"tool": "list_loops",
"tags": [],
"reasons": {}
},
{
"tool": "close_loop",
"tags": [],
"reasons": {}
},
{
"tool": "weekly_review",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "2fe68e1a85dbaf1428b2983e3f211651a5935127ab4ad29597ebd72d1357b554",
"stats": {
"tools": 11,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 11,
"medium": 1,
"low": 0,
"info": 1
}
}
}