Parts — 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.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "parts-mcp",
"source": {
"kind": "package",
"origin": "parts-mcp"
},
"server": {
"name": "parts-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-1.13"
},
"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 (22 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 (parts_mcp/internal/project_config.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`parts_mcp/internal/project_config.py:27`): 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": "parts_mcp/internal/project_config.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"--show-toplevel\"], cwd=str(start_p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "parts_mcp/internal/project_config.py",
"line": 27,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (parts_mcp/tools/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`parts_mcp/tools/cli.py:348`): 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": "parts_mcp/tools/cli.py"
},
"evidence": "y: result = subprocess.run( args, cwd=cwd, capture_output=Tr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "parts_mcp/tools/cli.py",
"line": 348,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (parts_mcp/tools/kicad_ctrl.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`parts_mcp/tools/kicad_ctrl.py:391`): 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": "parts_mcp/tools/kicad_ctrl.py"
},
"evidence": "proc = subprocess.run( [\"patch\", \"-p1\", \"--no-backup-if-mismatch\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "parts_mcp/tools/kicad_ctrl.py",
"line": 391,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (parts_mcp/utils/kicad_utils.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`parts_mcp/utils/kicad_utils.py:289`): 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": "parts_mcp/utils/kicad_utils.py"
},
"evidence": "d)}\") result = subprocess.run( cmd, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "parts_mcp/utils/kicad_utils.py",
"line": 289,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/verify_attribute_guard.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/verify_attribute_guard.py:28`): 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": "scripts/verify_attribute_guard.py"
},
"evidence": "git HEAD.\"\"\" src = subprocess.run( [\"git\", \"-C\", str(REPO), \"show\", \"HEAD:parts_mcp/utils/api_client.py\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/verify_attribute_guard.py",
"line": 28,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/unit/test_eda_export_tamarin.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_eda_export_tamarin.py:48`): 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": "tests/unit/test_eda_export_tamarin.py"
},
"evidence": "(\"bom\") / \"bom.csv\" subprocess.run( [\"kicad-cli\", \"sch\", \"export\", \"bom\", \"--fields\", \"Reference,Va",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/unit/test_eda_export_tamarin.py",
"line": 48,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "extract_bom_from_kicad",
"tags": [],
"reasons": {}
},
{
"tool": "find_kicad_projects",
"tags": [],
"reasons": {}
},
{
"tool": "match_components_to_parts",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_kicad_project",
"tags": [],
"reasons": {}
},
{
"tool": "extract_netlist_from_project",
"tags": [],
"reasons": {}
},
{
"tool": "open_in_kicad",
"tags": [],
"reasons": {}
},
{
"tool": "highlight_net_traces",
"tags": [],
"reasons": {}
},
{
"tool": "convert_kicad_version",
"tags": [],
"reasons": {}
},
{
"tool": "convert_allegro",
"tags": [],
"reasons": {}
},
{
"tool": "convert_pads",
"tags": [],
"reasons": {}
},
{
"tool": "convert_geda",
"tags": [],
"reasons": {}
},
{
"tool": "convert_protel",
"tags": [],
"reasons": {}
},
{
"tool": "export_parts_to_kicad",
"tags": [],
"reasons": {}
},
{
"tool": "sch_erc_categorize",
"tags": [],
"reasons": {}
},
{
"tool": "sch_pin_position",
"tags": [],
"reasons": {}
},
{
"tool": "sch_check_structure",
"tags": [],
"reasons": {}
},
{
"tool": "sch_remove_wires",
"tags": [],
"reasons": {}
},
{
"tool": "sch_libsync",
"tags": [],
"reasons": {}
},
{
"tool": "doc_wip_new",
"tags": [],
"reasons": {}
},
{
"tool": "doc_wip_preview",
"tags": [],
"reasons": {}
},
{
"tool": "doc_wip_send",
"tags": [],
"reasons": {}
},
{
"tool": "doc_wip_history",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "2b6296ac7e52074c57a6c3b8c4d83e4e0e8f32cdbfacc01deb3398d834c32bc2",
"stats": {
"tools": 22,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 2,
"info": 0
}
}
}