Isabelle — 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": "isabelle-mcp",
"source": {
"kind": "package",
"origin": "isabelle-mcp"
},
"server": {
"name": "isabelle-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": [
"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 (24 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-CAP-001",
"title": "Tool \"isabelle_eval_at_breakpoint\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"isabelle_eval_at_breakpoint\" appears to run shell commands or evaluate code (keyword \"eval\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "isabelle_eval_at_breakpoint"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/isabelle_mcp/component.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/isabelle_mcp/component.py:196`): 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/isabelle_mcp/component.py"
},
"evidence": "to edit.\"\"\" proc = subprocess.run( [c.isabelle, \"components\", op, path], capture_output=True, text=True, ti",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/isabelle_mcp/component.py",
"line": 196,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/isabelle_mcp/install.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/isabelle_mcp/install.py:51`): 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/isabelle_mcp/install.py"
},
"evidence": "tr) -> None: proc = subprocess.run(add_cmd) if proc.returncode != 0: _eprint(f\"error: '{client} mcp add'",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/isabelle_mcp/install.py",
"line": 51,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/isabelle_mcp/lsp_client.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/isabelle_mcp/lsp_client.py:190`): 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/isabelle_mcp/lsp_client.py"
},
"evidence": "try: out = subprocess.run( [\"isabelle\", \"version\"], capture_output=True, te",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/isabelle_mcp/lsp_client.py",
"line": 190,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/isabelle_mcp/utils/isabelle_symbols.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/isabelle_mcp/utils/isabelle_symbols.py:130`): 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/isabelle_mcp/utils/isabelle_symbols.py"
},
"evidence": "YMBOLS``.\"\"\" home = os.popen(\"isabelle getenv -b ISABELLE_HOME\").read().strip() home_user = os.popen(\"isabelle g",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/isabelle_mcp/utils/isabelle_symbols.py",
"line": 130,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"isabelle_eval_at_breakpoint\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"isabelle_eval_at_breakpoint\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "isabelle_eval_at_breakpoint"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_component.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_component.py:111`): 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_component.py"
},
"evidence": "(*args): return subprocess.run([\"isabelle\", *args], capture_output=True, text=True) def test_fresh_user(sel",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_component.py",
"line": 111,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"isabelle-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "isabelle-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "isabelle_launch",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_terminate",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_evaluate_to",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_evaluation_status",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_cancel_evaluation",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_hover",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_definition",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_local_occurrences",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_goal",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_find_theorems",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_command_output",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_command_status",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_session_info",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_set_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_del_breakpoints",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_list_breakpoints",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_list_breakable_sites",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_enable_all_breakpoints",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_disable_all_breakpoints",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_debug_state",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_eval_at_breakpoint",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "isabelle_locals_at_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_continue_breakpoint",
"tags": [],
"reasons": {}
},
{
"tool": "isabelle_step_at_breakpoint",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "42c1db0fd27ce02da73d583bd938799af89e0a46749526429e20e1cb12f84fc5",
"stats": {
"tools": 24,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 2,
"info": 1
}
}
}