Gds Agent — 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": "gds-agent",
"source": {
"kind": "package",
"origin": "gds-agent"
},
"server": {
"name": "gds-agent"
}
},
"grade": "A",
"score": {
"score": 99,
"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": "minimal",
"label": "capability blast radius (minimal) — client exposure if the model is manipulated",
"appliedPenalty": 0
},
{
"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": "minimal",
"reasons": [],
"tags": []
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (71 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 packaging/dev tooling (tests/conftest.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/conftest.py:25`): 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/conftest.py"
},
"evidence": "=True) result = subprocess.run( [\"docker\", \"ps\", \"-a\", \"--filter\", f\"ancestor={NEO4J_IMAGE}\", \"-q\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/conftest.py",
"line": 25,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "article_rank",
"tags": [],
"reasons": {}
},
{
"tool": "articulation_points",
"tags": [],
"reasons": {}
},
{
"tool": "betweenness_centrality",
"tags": [],
"reasons": {}
},
{
"tool": "bridges",
"tags": [],
"reasons": {}
},
{
"tool": "CELF",
"tags": [],
"reasons": {}
},
{
"tool": "closeness_centrality",
"tags": [],
"reasons": {}
},
{
"tool": "degree_centrality",
"tags": [],
"reasons": {}
},
{
"tool": "eigenvector_centrality",
"tags": [],
"reasons": {}
},
{
"tool": "pagerank",
"tags": [],
"reasons": {}
},
{
"tool": "harmonic_centrality",
"tags": [],
"reasons": {}
},
{
"tool": "HITS",
"tags": [],
"reasons": {}
},
{
"tool": "conductance",
"tags": [],
"reasons": {}
},
{
"tool": "HDBSCAN",
"tags": [],
"reasons": {}
},
{
"tool": "k_core_decomposition",
"tags": [],
"reasons": {}
},
{
"tool": "k_1_coloring",
"tags": [],
"reasons": {}
},
{
"tool": "k_means_clustering",
"tags": [],
"reasons": {}
},
{
"tool": "label_propagation",
"tags": [],
"reasons": {}
},
{
"tool": "leiden",
"tags": [],
"reasons": {}
},
{
"tool": "local_clustering_coefficient",
"tags": [],
"reasons": {}
},
{
"tool": "louvain",
"tags": [],
"reasons": {}
},
{
"tool": "modularity_metric",
"tags": [],
"reasons": {}
},
{
"tool": "modularity_optimization",
"tags": [],
"reasons": {}
},
{
"tool": "strongly_connected_components",
"tags": [],
"reasons": {}
},
{
"tool": "triangle_count",
"tags": [],
"reasons": {}
},
{
"tool": "weakly_connected_components",
"tags": [],
"reasons": {}
},
{
"tool": "approximate_maximum_k_cut",
"tags": [],
"reasons": {}
},
{
"tool": "speaker_listener_label_propagation",
"tags": [],
"reasons": {}
},
{
"tool": "fast_rp",
"tags": [],
"reasons": {}
},
{
"tool": "node2vec",
"tags": [],
"reasons": {}
},
{
"tool": "hashgnn",
"tags": [],
"reasons": {}
},
{
"tool": "graph_sage_train",
"tags": [],
"reasons": {}
},
{
"tool": "graph_sage_predict",
"tags": [],
"reasons": {}
},
{
"tool": "project_graph_cypher",
"tags": [],
"reasons": {}
},
{
"tool": "drop_graph",
"tags": [],
"reasons": {}
},
{
"tool": "list_graphs",
"tags": [],
"reasons": {}
},
{
"tool": "get_graph_info",
"tags": [],
"reasons": {}
},
{
"tool": "stream_node_properties",
"tags": [],
"reasons": {}
},
{
"tool": "stream_relationship_properties",
"tags": [],
"reasons": {}
},
{
"tool": "stream_relationships",
"tags": [],
"reasons": {}
},
{
"tool": "train_node_classification_model",
"tags": [],
"reasons": {}
},
{
"tool": "predict_node_classification",
"tags": [],
"reasons": {}
},
{
"tool": "train_link_prediction_model",
"tags": [],
"reasons": {}
},
{
"tool": "predict_link_prediction",
"tags": [],
"reasons": {}
},
{
"tool": "train_node_regression_model",
"tags": [],
"reasons": {}
},
{
"tool": "predict_node_regression",
"tags": [],
"reasons": {}
},
{
"tool": "list_models",
"tags": [],
"reasons": {}
},
{
"tool": "drop_model",
"tags": [],
"reasons": {}
},
{
"tool": "find_shortest_path",
"tags": [],
"reasons": {}
},
{
"tool": "delta_stepping_shortest_path",
"tags": [],
"reasons": {}
},
{
"tool": "dijkstra_single_source_shortest_path",
"tags": [],
"reasons": {}
},
{
"tool": "a_star_shortest_path",
"tags": [],
"reasons": {}
},
{
"tool": "yens_shortest_paths",
"tags": [],
"reasons": {}
},
{
"tool": "minimum_weight_spanning_tree",
"tags": [],
"reasons": {}
},
{
"tool": "minimum_directed_steiner_tree",
"tags": [],
"reasons": {}
},
{
"tool": "prize_collecting_steiner_tree",
"tags": [],
"reasons": {}
},
{
"tool": "all_pairs_shortest_paths",
"tags": [],
"reasons": {}
},
{
"tool": "random_walk",
"tags": [],
"reasons": {}
},
{
"tool": "breadth_first_search",
"tags": [],
"reasons": {}
},
{
"tool": "depth_first_search",
"tags": [],
"reasons": {}
},
{
"tool": "bellman_ford_single_source_shortest_path",
"tags": [],
"reasons": {}
},
{
"tool": "longest_path",
"tags": [],
"reasons": {}
},
{
"tool": "max_flow",
"tags": [],
"reasons": {}
},
{
"tool": "list_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "delete_session",
"tags": [],
"reasons": {}
},
{
"tool": "create_session",
"tags": [],
"reasons": {}
},
{
"tool": "get_node_properties_keys",
"tags": [],
"reasons": {}
},
{
"tool": "get_relationship_properties_keys",
"tags": [],
"reasons": {}
},
{
"tool": "get_node_labels",
"tags": [],
"reasons": {}
},
{
"tool": "get_relationship_types",
"tags": [],
"reasons": {}
},
{
"tool": "node_similarity",
"tags": [],
"reasons": {}
},
{
"tool": "k_nearest_neighbors",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "192051f357499fa004d1fc470a0c94eb6c675b71723518601dfd3f661e95f5b4",
"stats": {
"tools": 71,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 0,
"low": 1,
"info": 0
}
}
}