Magic Api — 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": "magic-api-mcp-server",
"source": {
"kind": "package",
"origin": "magic-api-mcp-server"
},
"server": {
"name": "magic-api-mcp-server"
}
},
"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 (57 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 (magicapi_tools/utils/ws.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`magicapi_tools/utils/ws.py:784`): 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": "magicapi_tools/utils/ws.py"
},
"evidence": "ss result = subprocess.run([ sys.executable, extract_script, '--url', 'http:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "magicapi_tools/utils/ws.py",
"line": 784,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (test/test_docker.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`test/test_docker.py:22`): 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": "test/test_docker.py"
},
"evidence": "try: result = subprocess.run(cmd, capture_output=True, text=True, timeout=30) if result.returncode ==",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "test/test_docker.py",
"line": 22,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "call_magic_api",
"tags": [],
"reasons": {}
},
{
"tool": "list_backups",
"tags": [],
"reasons": {}
},
{
"tool": "get_backup_history",
"tags": [],
"reasons": {}
},
{
"tool": "get_backup_content",
"tags": [],
"reasons": {}
},
{
"tool": "rollback_backup",
"tags": [],
"reasons": {}
},
{
"tool": "create_full_backup",
"tags": [],
"reasons": {}
},
{
"tool": "list_magic_api_classes",
"tags": [],
"reasons": {}
},
{
"tool": "search_magic_api_classes",
"tags": [],
"reasons": {}
},
{
"tool": "search_magic_api_classes_txt",
"tags": [],
"reasons": {}
},
{
"tool": "get_magic_api_class_details",
"tags": [],
"reasons": {}
},
{
"tool": "generate_crud_api",
"tags": [],
"reasons": {}
},
{
"tool": "generate_database_query",
"tags": [],
"reasons": {}
},
{
"tool": "generate_api_from_example",
"tags": [],
"reasons": {}
},
{
"tool": "generate_error_handling",
"tags": [],
"reasons": {}
},
{
"tool": "generate_transaction_code",
"tags": [],
"reasons": {}
},
{
"tool": "generate_lambda_operations",
"tags": [],
"reasons": {}
},
{
"tool": "call_magic_api_with_debug",
"tags": [],
"reasons": {}
},
{
"tool": "get_latest_breakpoint_status",
"tags": [],
"reasons": {}
},
{
"tool": "resume_from_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "step_over_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "step_into_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "step_out_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "set_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "remove_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "list_breakpoints",
"tags": [],
"reasons": {}
},
{
"tool": "execute_debug_session",
"tags": [],
"reasons": {}
},
{
"tool": "get_debug_status",
"tags": [],
"reasons": {}
},
{
"tool": "inspect_ws_environments",
"tags": [],
"reasons": {}
},
{
"tool": "get_websocket_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_magic_script_syntax",
"tags": [],
"reasons": {}
},
{
"tool": "get_full_magic_script_syntax",
"tags": [],
"reasons": {}
},
{
"tool": "get_magic_script_examples",
"tags": [],
"reasons": {}
},
{
"tool": "get_magic_api_docs",
"tags": [],
"reasons": {}
},
{
"tool": "get_best_practices",
"tags": [],
"reasons": {}
},
{
"tool": "get_common_pitfalls",
"tags": [],
"reasons": {}
},
{
"tool": "get_development_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "get_documentation",
"tags": [],
"reasons": {}
},
{
"tool": "get_examples",
"tags": [],
"reasons": {}
},
{
"tool": "search_knowledge",
"tags": [],
"reasons": {}
},
{
"tool": "get_knowledge_overview",
"tags": [],
"reasons": {}
},
{
"tool": "get_practices_guide",
"tags": [],
"reasons": {}
},
{
"tool": "get_api_details_by_path",
"tags": [],
"reasons": {}
},
{
"tool": "search_api_endpoints",
"tags": [],
"reasons": {}
},
{
"tool": "get_resource_tree",
"tags": [],
"reasons": {}
},
{
"tool": "save_group",
"tags": [],
"reasons": {}
},
{
"tool": "save_api_endpoint",
"tags": [],
"reasons": {}
},
{
"tool": "copy_resource",
"tags": [],
"reasons": {}
},
{
"tool": "move_resource",
"tags": [],
"reasons": {}
},
{
"tool": "delete_resource",
"tags": [],
"reasons": {}
},
{
"tool": "list_resource_groups",
"tags": [],
"reasons": {}
},
{
"tool": "export_resource_tree",
"tags": [],
"reasons": {}
},
{
"tool": "read_set_lock_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_resource_statistics",
"tags": [],
"reasons": {}
},
{
"tool": "replace_api_script",
"tags": [],
"reasons": {}
},
{
"tool": "search_api_scripts",
"tags": [],
"reasons": {}
},
{
"tool": "search_todo_comments",
"tags": [],
"reasons": {}
},
{
"tool": "get_assistant_metadata",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "523751d56b291fa0c29749543921d1f5c8da72362a3d58d1d18c44b448f2b6d7",
"stats": {
"tools": 57,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 0,
"low": 1,
"info": 0
}
}
}