Dax Query — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "dax-query-mcp",
"source": {
"kind": "package",
"origin": "dax-query-mcp"
},
"server": {
"name": "dax-query-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-1.9"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"external-sink",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (50 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 (dax_query_mcp/copilot_guard.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dax_query_mcp/copilot_guard.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": "dax_query_mcp/copilot_guard.py"
},
"evidence": "ry: completed = subprocess.run( command, cwd=repo_root, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dax_query_mcp/copilot_guard.py",
"line": 153,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dax_query_mcp/executor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dax_query_mcp/executor.py:236`): 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": "dax_query_mcp/executor.py"
},
"evidence": "table() completed = subprocess.run( [ az_executable, \"account\", \"get-acc",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dax_query_mcp/executor.py",
"line": 236,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dax_query_mcp/mcp_server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dax_query_mcp/mcp_server.py:224`): 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": "dax_query_mcp/mcp_server.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"--short\", \"HEAD\"], cwd=repo_root,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dax_query_mcp/mcp_server.py",
"line": 224,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dax_query_mcp/scaffold.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dax_query_mcp/scaffold.py:187`): 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": "dax_query_mcp/scaffold.py"
},
"evidence": "e() completed = subprocess.run( [ az_executable, \"account\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dax_query_mcp/scaffold.py",
"line": 187,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_mcp_server.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_mcp_server.py:2146`): 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/test_mcp_server.py"
},
"evidence": ": str(script_path)} exec(script_path.read_text(encoding=\"utf-8\"), namespace) monkeypatch.setattr(\"sys.argv\", [\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_mcp_server.py",
"line": 2146,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_scaffold.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_scaffold.py:218`): 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/test_scaffold.py"
},
"evidence": "t(encoding=\"utf-8\") exec(script, namespace) with pytest.raises(RuntimeError, match=\"dataset-only executeQueries",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_scaffold.py",
"line": 218,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"dax-query-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "dax-query-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "server_info",
"tags": [],
"reasons": {}
},
{
"tool": "list_connections",
"tags": [],
"reasons": {}
},
{
"tool": "get_connection_context",
"tags": [],
"reasons": {}
},
{
"tool": "search_connection_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_data_dictionary",
"tags": [],
"reasons": {}
},
{
"tool": "get_schema",
"tags": [],
"reasons": {}
},
{
"tool": "get_context_bundle",
"tags": [],
"reasons": {}
},
{
"tool": "get_table_detail",
"tags": [],
"reasons": {}
},
{
"tool": "get_measure_detail",
"tags": [],
"reasons": {}
},
{
"tool": "get_relationships",
"tags": [],
"reasons": {}
},
{
"tool": "get_filter_suggestions",
"tags": [],
"reasons": {}
},
{
"tool": "check_context_staleness",
"tags": [],
"reasons": {}
},
{
"tool": "check_ai_readiness",
"tags": [],
"reasons": {}
},
{
"tool": "probe_tmschema_capabilities",
"tags": [],
"reasons": {}
},
{
"tool": "run_connection_query",
"tags": [],
"reasons": {}
},
{
"tool": "get_query_builder_schema",
"tags": [],
"reasons": {}
},
{
"tool": "save_query_builder",
"tags": [],
"reasons": {}
},
{
"tool": "get_query_builder",
"tags": [],
"reasons": {}
},
{
"tool": "inspect_connection",
"tags": [],
"reasons": {}
},
{
"tool": "list_queries",
"tags": [],
"reasons": {}
},
{
"tool": "run_named_query",
"tags": [],
"reasons": {}
},
{
"tool": "run_ad_hoc_query",
"tags": [],
"reasons": {}
},
{
"tool": "inspect_model_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "search_columns",
"tags": [],
"reasons": {}
},
{
"tool": "search_measures",
"tags": [],
"reasons": {}
},
{
"tool": "copy_to_clipboard",
"tags": [],
"reasons": {}
},
{
"tool": "scaffold_dax_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "scaffold_streamlit_app",
"tags": [],
"reasons": {}
},
{
"tool": "export_to_csv",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"export_to\""
]
}
},
{
"tool": "scaffold_power_query",
"tags": [],
"reasons": {}
},
{
"tool": "quick_chart",
"tags": [],
"reasons": {}
},
{
"tool": "generate_data_dictionary",
"tags": [],
"reasons": {}
},
{
"tool": "diff_data_dictionary",
"tags": [],
"reasons": {}
},
{
"tool": "merge_data_dictionary",
"tags": [],
"reasons": {}
},
{
"tool": "review_data_dictionary_update",
"tags": [],
"reasons": {}
},
{
"tool": "save_validated_query",
"tags": [],
"reasons": {}
},
{
"tool": "list_validated_queries",
"tags": [],
"reasons": {}
},
{
"tool": "search_validated_queries",
"tags": [],
"reasons": {}
},
{
"tool": "validate_query_library",
"tags": [],
"reasons": {}
},
{
"tool": "save_to_workstation",
"tags": [],
"reasons": {}
},
{
"tool": "list_workstation",
"tags": [],
"reasons": {}
},
{
"tool": "remove_from_workstation",
"tags": [],
"reasons": {}
},
{
"tool": "clear_workstation",
"tags": [],
"reasons": {}
},
{
"tool": "create_query_pack",
"tags": [],
"reasons": {}
},
{
"tool": "save_query_to_pack",
"tags": [],
"reasons": {}
},
{
"tool": "list_query_pack",
"tags": [],
"reasons": {}
},
{
"tool": "validate_query_pack",
"tags": [],
"reasons": {}
},
{
"tool": "describe_query_pack",
"tags": [],
"reasons": {}
},
{
"tool": "export_query_pack",
"tags": [],
"reasons": {}
},
{
"tool": "export_workstation",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "988edb2ed6e10f7bfdfbb46868b9e0db7bedce97bc5fb31febd6c54734121ecc",
"stats": {
"tools": 50,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 2,
"info": 1
}
}
}