Dbutils — 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": "mcp-dbutils",
"source": {
"kind": "package",
"origin": "mcp-dbutils"
},
"server": {
"name": "mcp-dbutils"
}
},
"grade": "A",
"score": {
"score": 95,
"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": "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": "moderate",
"reasons": [
"reads sensitive or local data"
],
"tags": [
"sensitive-source"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (14 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-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/integration/test_mysql.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_mysql.py:33`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/integration/test_mysql.py"
},
"evidence": "\") schema = eval(schema_str) assert schema[\"columns\"][0][\"name\"] == \"id\" assert sche",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/integration/test_mysql.py",
"line": 33,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/integration/test_mysql_handler_extended.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_mysql_handler_extended.py:191`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/integration/test_mysql_handler_extended.py"
},
"evidence": ") result = eval(result_str) assert \"columns\" in result assert \"rows\" in result",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/integration/test_mysql_handler_extended.py",
"line": 191,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/integration/test_postgres.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_postgres.py:31`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/integration/test_postgres.py"
},
"evidence": "\") schema = eval(schema_str) assert schema[\"columns\"][0][\"name\"] == \"id\" assert sche",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/integration/test_postgres.py",
"line": 31,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/integration/test_sqlite.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_sqlite.py:26`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/integration/test_sqlite.py"
},
"evidence": "\") schema = eval(schema_str) assert schema[\"columns\"][0][\"name\"] == \"id\" assert sche",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/integration/test_sqlite.py",
"line": 26,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/integration/test_sqlite_handler_extended.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_sqlite_handler_extended.py:136`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/integration/test_sqlite_handler_extended.py"
},
"evidence": ") result = eval(result_str) assert \"columns\" in result assert \"rows\" in result",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/integration/test_sqlite_handler_extended.py",
"line": 136,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/unit/test_mysql_server.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_mysql_server.py:151`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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_mysql_server.py"
},
"evidence": "result_dict = eval(result) # Convert string representation to dict assert len(result_dict[\"column",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/unit/test_mysql_server.py",
"line": 151,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/unit/test_postgres_server.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_postgres_server.py:156`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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_postgres_server.py"
},
"evidence": "result_dict = eval(result) # Convert string representation to dict assert len(result_dict[\"column",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/unit/test_postgres_server.py",
"line": 156,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/integration/test_sqlite_handler_extended.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_sqlite_handler_extended.py:153`): 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/integration/test_sqlite_handler_extended.py"
},
"evidence": "\"path\"] os.system(f\"\"\" sqlite3 {path} ' CREATE TABLE IF NOT EXIS",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/integration/test_sqlite_handler_extended.py",
"line": 153,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"mcp-dbutils\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "mcp-dbutils"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"mcp-dbutils\" 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": "mcp-dbutils"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "dbutils-list-connections",
"tags": [],
"reasons": {}
},
{
"tool": "dbutils-execute-write",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"sql\""
]
}
},
{
"tool": "dbutils-run-query",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"sql\""
]
}
},
{
"tool": "dbutils-list-tables",
"tags": [],
"reasons": {}
},
{
"tool": "dbutils-describe-table",
"tags": [],
"reasons": {}
},
{
"tool": "dbutils-get-ddl",
"tags": [],
"reasons": {}
},
{
"tool": "dbutils-list-indexes",
"tags": [],
"reasons": {}
},
{
"tool": "dbutils-get-stats",
"tags": [],
"reasons": {}
},
{
"tool": "dbutils-list-constraints",
"tags": [],
"reasons": {}
},
{
"tool": "dbutils-explain-query",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"sql_query\"",
"parameter \"sql\""
]
}
},
{
"tool": "dbutils-get-performance",
"tags": [],
"reasons": {}
},
{
"tool": "dbutils-analyze-query",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"sql_query\"",
"parameter \"sql\""
]
}
},
{
"tool": "dbutils-get-audit-logs",
"tags": [],
"reasons": {}
},
{
"tool": "query",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"sql\""
]
}
}
],
"surfaceDigest": "566859c2ccda49ffc4fd7d0d61fa8b109c98a718cbb38ffac41bc123e16c2681",
"stats": {
"tools": 14,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 0,
"low": 8,
"info": 2
}
}
}