Kratos — 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": "kratos-mcp-server",
"source": {
"kind": "package",
"origin": "kratos-mcp-server"
},
"server": {
"name": "kratos-mcp-server"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "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-1.9"
},
"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 (40 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 (src/kratos_mcp/bridge.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/kratos_mcp/bridge.py:87`): 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": "src/kratos_mcp/bridge.py"
},
"evidence": "try: proc = subprocess.run( [env.python, \"-m\", \"kratos_mcp.worker\", \"--request-file",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/kratos_mcp/bridge.py",
"line": 87,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/kratos_mcp/jobs.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/kratos_mcp/jobs.py:110`): 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": "src/kratos_mcp/jobs.py"
},
"evidence": ".log\", \"wb\") proc = subprocess.Popen( cmd, env=run_env, stdout=log, stderr=subprocess.STDOUT, stdin=",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/kratos_mcp/jobs.py",
"line": 110,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/kratos_mcp/kratos_env.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/kratos_mcp/kratos_env.py:129`): 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": "src/kratos_mcp/kratos_env.py"
},
"evidence": "our stdout. probe = subprocess.run( [sys.executable, \"-c\", \"import KratosMultiphysics\"], capture_out",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/kratos_mcp/kratos_env.py",
"line": 129,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/kratos_mcp/render_worker.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/kratos_mcp/render_worker.py:180`): 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": "src/kratos_mcp/render_worker.py"
},
"evidence": "= os.pipe() proc = subprocess.Popen( [\"Xvfb\", \"-displayfd\", str(write_fd), \"-screen\", \"0\", \"1280x1024x24\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/kratos_mcp/render_worker.py",
"line": 180,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/kratos_mcp/tools/visualize.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/kratos_mcp/tools/visualize.py:82`): 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": "src/kratos_mcp/tools/visualize.py"
},
"evidence": "try: proc = subprocess.run( [sys.executable, \"-m\", \"kratos_mcp.render_worker\", \"--r",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/kratos_mcp/tools/visualize.py",
"line": 82,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_visualize.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_visualize.py:115`): 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_visualize.py"
},
"evidence": "gs\": args})) proc = subprocess.run( [sys.executable, \"-m\", \"kratos_mcp.render_worker\", \"--request-f",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_visualize.py",
"line": 115,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"kratos-mcp-server\" 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": "kratos-mcp-server"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "kratos_check_installation",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_install",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_list_applications",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_list_elements",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_list_conditions",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_list_constitutive_laws",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_list_variables",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_list_solvers",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_list_processes",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_get_process_defaults",
"tags": [],
"reasons": {}
},
{
"tool": "kratos_get_solver_defaults",
"tags": [],
"reasons": {}
},
{
"tool": "explain_project_parameters",
"tags": [],
"reasons": {}
},
{
"tool": "export_case_to_flowgraph",
"tags": [],
"reasons": {}
},
{
"tool": "import_flowgraph_to_case",
"tags": [],
"reasons": {}
},
{
"tool": "mdpa_inspect",
"tags": [],
"reasons": {}
},
{
"tool": "mdpa_validate",
"tags": [],
"reasons": {}
},
{
"tool": "mdpa_create_structured_mesh",
"tags": [],
"reasons": {}
},
{
"tool": "mdpa_get_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "results_list",
"tags": [],
"reasons": {}
},
{
"tool": "results_summary",
"tags": [],
"reasons": {}
},
{
"tool": "results_probe",
"tags": [],
"reasons": {}
},
{
"tool": "results_convergence",
"tags": [],
"reasons": {}
},
{
"tool": "list_templates",
"tags": [],
"reasons": {}
},
{
"tool": "create_project_parameters",
"tags": [],
"reasons": {}
},
{
"tool": "list_material_presets",
"tags": [],
"reasons": {}
},
{
"tool": "list_linear_solver_presets",
"tags": [],
"reasons": {}
},
{
"tool": "create_materials",
"tags": [],
"reasons": {}
},
{
"tool": "create_project",
"tags": [],
"reasons": {}
},
{
"tool": "create_multistage_project",
"tags": [],
"reasons": {}
},
{
"tool": "add_boundary_condition",
"tags": [],
"reasons": {}
},
{
"tool": "add_output_process",
"tags": [],
"reasons": {}
},
{
"tool": "validate_project_parameters",
"tags": [],
"reasons": {}
},
{
"tool": "run_simulation",
"tags": [],
"reasons": {}
},
{
"tool": "validate_case",
"tags": [],
"reasons": {}
},
{
"tool": "job_status",
"tags": [],
"reasons": {}
},
{
"tool": "job_list",
"tags": [],
"reasons": {}
},
{
"tool": "job_logs",
"tags": [],
"reasons": {}
},
{
"tool": "job_cancel",
"tags": [],
"reasons": {}
},
{
"tool": "results_render",
"tags": [],
"reasons": {}
},
{
"tool": "results_animate",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "92ab42191830f8c41bd69e1c25acefe2a96390ce58853ad11342c05c808a6723",
"stats": {
"tools": 40,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 1,
"info": 1
}
}
}