Ds Toolkit — 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-ds-toolkit-server",
"source": {
"kind": "package",
"origin": "mcp-ds-toolkit-server"
},
"server": {
"name": "mcp-ds-toolkit-server"
}
},
"grade": "B",
"score": {
"score": 85,
"threatScore": 89,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 11.03,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.25,
"appliedPenalty": 1.58
},
{
"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": "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": "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 (30 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-005",
"title": "Dynamic module load from a non-literal (src/mcp_ds_toolkit_server/server.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`src/mcp_ds_toolkit_server/server.py:202`): 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_ds_toolkit_server/server.py"
},
"evidence": "try: __import__(module_name) except ImportError as e: error_msg = f\"Criti",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "src/mcp_ds_toolkit_server/server.py",
"line": 202,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (src/mcp_ds_toolkit_server/training/trainer.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_ds_toolkit_server/training/trainer.py:721`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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_ds_toolkit_server/training/trainer.py"
},
"evidence": "model = pickle.load(f) self.logger.info(f\"Model loaded from {model_path}\") retu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "src/mcp_ds_toolkit_server/training/trainer.py",
"line": 721,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (src/mcp_ds_toolkit_server/utils/model_resolver.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_ds_toolkit_server/utils/model_resolver.py:132`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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_ds_toolkit_server/utils/model_resolver.py"
},
"evidence": "model = pickle.load(f) if isinstance(model, BaseEstimator):",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "src/mcp_ds_toolkit_server/utils/model_resolver.py",
"line": 132,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (src/mcp_ds_toolkit_server/utils/persistence.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/mcp_ds_toolkit_server/utils/persistence.py:133`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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_ds_toolkit_server/utils/persistence.py"
},
"evidence": "8')) return pickle.loads(model_bytes) else: raise ValueError(f\"Unsupported encoding for",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "src/mcp_ds_toolkit_server/utils/persistence.py",
"line": 133,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"output_path\" on \"export_dataset\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"export_dataset\" takes a path parameter \"output_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "export_dataset",
"field": "inputSchema.properties.output_path"
},
"data": {
"param": "output_path"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "load_dataset",
"tags": [],
"reasons": {}
},
{
"tool": "validate_dataset",
"tags": [],
"reasons": {}
},
{
"tool": "profile_dataset",
"tags": [],
"reasons": {}
},
{
"tool": "preprocess_dataset",
"tags": [],
"reasons": {}
},
{
"tool": "clean_dataset",
"tags": [],
"reasons": {}
},
{
"tool": "split_dataset",
"tags": [],
"reasons": {}
},
{
"tool": "list_datasets",
"tags": [],
"reasons": {}
},
{
"tool": "get_dataset_info",
"tags": [],
"reasons": {}
},
{
"tool": "compare_datasets",
"tags": [],
"reasons": {}
},
{
"tool": "batch_process_datasets",
"tags": [],
"reasons": {}
},
{
"tool": "sample_dataset",
"tags": [],
"reasons": {}
},
{
"tool": "export_dataset",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"export_data\""
]
}
},
{
"tool": "remove_dataset",
"tags": [],
"reasons": {}
},
{
"tool": "clear_all_data",
"tags": [],
"reasons": {}
},
{
"tool": "create_experiment",
"tags": [],
"reasons": {}
},
{
"tool": "start_run",
"tags": [],
"reasons": {}
},
{
"tool": "log_params",
"tags": [],
"reasons": {}
},
{
"tool": "log_metrics",
"tags": [],
"reasons": {}
},
{
"tool": "log_artifact",
"tags": [],
"reasons": {}
},
{
"tool": "end_run",
"tags": [],
"reasons": {}
},
{
"tool": "list_experiments",
"tags": [],
"reasons": {}
},
{
"tool": "get_experiment",
"tags": [],
"reasons": {}
},
{
"tool": "list_runs",
"tags": [],
"reasons": {}
},
{
"tool": "compare_runs",
"tags": [],
"reasons": {}
},
{
"tool": "train_model",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate_model",
"tags": [],
"reasons": {}
},
{
"tool": "compare_models",
"tags": [],
"reasons": {}
},
{
"tool": "tune_hyperparameters",
"tags": [],
"reasons": {}
},
{
"tool": "get_model_info",
"tags": [],
"reasons": {}
},
{
"tool": "list_algorithms",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d990bdf33204acc1177efb5cf6b02dc21c6931a49bb1820c21c42900d707bd49",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 4,
"low": 1,
"info": 0
}
}
}