Claude Pascal — 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": "claude-pascal-mcp",
"source": {
"kind": "package",
"origin": "claude-pascal-mcp"
},
"server": {
"name": "claude-pascal-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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (53 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/pascal_mcp/adb.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/pascal_mcp/adb.py:118`): 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/pascal_mcp/adb.py"
},
"evidence": "xtend(args) return subprocess.run( cmd, capture_output=True, text=not binary, timeo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pascal_mcp/adb.py",
"line": 118,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/pascal_mcp/compiler.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/pascal_mcp/compiler.py:74`): 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/pascal_mcp/compiler.py"
},
"evidence": "try: result = subprocess.run( [fpc_path, \"-iV\"], capture_output=True, text=True, timeo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pascal_mcp/compiler.py",
"line": 74,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/pascal_mcp/installer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/pascal_mcp/installer.py:39`): 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/pascal_mcp/installer.py"
},
"evidence": "try: result = subprocess.run( [fpc_exe, \"-iV\"], capture_output=True, text=True, timeou",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pascal_mcp/installer.py",
"line": 39,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/pascal_mcp/mac_ssh.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/pascal_mcp/mac_ssh.py:197`): 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/pascal_mcp/mac_ssh.py"
},
"evidence": "try: proc = subprocess.run( args, capture_output=True, text=True, timeout=timeout, e",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pascal_mcp/mac_ssh.py",
"line": 197,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/pascal_mcp/paclient.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/pascal_mcp/paclient.py:98`): 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/pascal_mcp/paclient.py"
},
"evidence": "ient, *args] return subprocess.run( cmd, capture_output=True, text=True, timeout=timeout, encoding=\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pascal_mcp/paclient.py",
"line": 98,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/pascal_mcp/preview_bridge.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/pascal_mcp/preview_bridge.py:109`): 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/pascal_mcp/preview_bridge.py"
},
"evidence": "try: proc = subprocess.Popen( [exe_path], stdout=subprocess.PIPE, stderr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pascal_mcp/preview_bridge.py",
"line": 109,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"claude-pascal-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "claude-pascal-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "get_compiler_info",
"tags": [],
"reasons": {}
},
{
"tool": "compile_pascal",
"tags": [],
"reasons": {}
},
{
"tool": "run_pascal",
"tags": [],
"reasons": {}
},
{
"tool": "check_syntax",
"tags": [],
"reasons": {}
},
{
"tool": "parse_form",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot_app",
"tags": [],
"reasons": {}
},
{
"tool": "list_app_windows",
"tags": [],
"reasons": {}
},
{
"tool": "launch_app",
"tags": [],
"reasons": {}
},
{
"tool": "compile_delphi_project",
"tags": [],
"reasons": {}
},
{
"tool": "build_dproj",
"tags": [],
"reasons": {}
},
{
"tool": "check_ios_deploy",
"tags": [],
"reasons": {}
},
{
"tool": "paserver_info",
"tags": [],
"reasons": {}
},
{
"tool": "paserver_check_connection",
"tags": [],
"reasons": {}
},
{
"tool": "paserver_scratch_dir",
"tags": [],
"reasons": {}
},
{
"tool": "paserver_get",
"tags": [],
"reasons": {}
},
{
"tool": "paserver_put",
"tags": [],
"reasons": {}
},
{
"tool": "mac_ssh_check",
"tags": [],
"reasons": {}
},
{
"tool": "mac_ssh_run",
"tags": [],
"reasons": {}
},
{
"tool": "sim_list",
"tags": [],
"reasons": {}
},
{
"tool": "sim_boot",
"tags": [],
"reasons": {}
},
{
"tool": "sim_shutdown",
"tags": [],
"reasons": {}
},
{
"tool": "sim_install",
"tags": [],
"reasons": {}
},
{
"tool": "sim_launch",
"tags": [],
"reasons": {}
},
{
"tool": "sim_terminate",
"tags": [],
"reasons": {}
},
{
"tool": "sim_uninstall",
"tags": [],
"reasons": {}
},
{
"tool": "sim_open_url",
"tags": [],
"reasons": {}
},
{
"tool": "sim_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "ios_codesign",
"tags": [],
"reasons": {}
},
{
"tool": "ios_create_ipa",
"tags": [],
"reasons": {}
},
{
"tool": "ios_install_ipa",
"tags": [],
"reasons": {}
},
{
"tool": "paserver_remove",
"tags": [],
"reasons": {}
},
{
"tool": "list_remote_profiles",
"tags": [],
"reasons": {}
},
{
"tool": "setup_fpc",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "focus_ide",
"tags": [],
"reasons": {}
},
{
"tool": "observe_ide",
"tags": [],
"reasons": {}
},
{
"tool": "read_ide_errors",
"tags": [],
"reasons": {}
},
{
"tool": "list_project_files",
"tags": [],
"reasons": {}
},
{
"tool": "app_click",
"tags": [],
"reasons": {}
},
{
"tool": "app_type",
"tags": [],
"reasons": {}
},
{
"tool": "app_key",
"tags": [],
"reasons": {}
},
{
"tool": "adb_devices",
"tags": [],
"reasons": {}
},
{
"tool": "adb_device_info",
"tags": [],
"reasons": {}
},
{
"tool": "adb_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "adb_tap",
"tags": [],
"reasons": {}
},
{
"tool": "adb_swipe",
"tags": [],
"reasons": {}
},
{
"tool": "adb_type_text",
"tags": [],
"reasons": {}
},
{
"tool": "adb_key",
"tags": [],
"reasons": {}
},
{
"tool": "adb_install",
"tags": [],
"reasons": {}
},
{
"tool": "adb_list_packages",
"tags": [],
"reasons": {}
},
{
"tool": "adb_launch_app",
"tags": [],
"reasons": {}
},
{
"tool": "adb_stop_app",
"tags": [],
"reasons": {}
},
{
"tool": "adb_push",
"tags": [],
"reasons": {}
},
{
"tool": "adb_pull",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "e5935fe503e244d0103242a373e10a9980532b6465428c6138af68dff8cf1dfd",
"stats": {
"tools": 53,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 0,
"low": 0,
"info": 1
}
}
}