Nerve — 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": "nerve-mcp",
"source": {
"kind": "package",
"origin": "nerve-mcp"
},
"server": {
"name": "nerve-mcp"
}
},
"grade": "B",
"score": {
"score": 89,
"threatScore": 100,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"sensitive-source",
"external-sink",
"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 (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-FLOW-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: nerve_storage → nerve_tree → nerve_lldb. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "nerve_storage → nerve_tree → nerve_lldb"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"nerve_storage"
],
"sources": [
"nerve_tree",
"nerve_storage"
],
"sinks": [
"nerve_network",
"nerve_lldb",
"nerve_sequence"
],
"path": [
"nerve_storage",
"nerve_tree",
"nerve_lldb"
],
"edges": [
{
"from": "nerve_storage",
"to": "nerve_tree",
"kind": "agent-mediated"
},
{
"from": "nerve_tree",
"to": "nerve_lldb",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"nerve_lldb\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"nerve_lldb\" appears to run shell commands or evaluate code (parameter \"command\"). 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": "nerve_lldb"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"nerve_sequence\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"nerve_sequence\" appears to run shell commands or evaluate code (parameter \"command\"). 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": "nerve_sequence"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:44`): 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": "dist/index.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 44
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"target\" on \"nerve_network\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"nerve_network\" takes a URL/host parameter \"target\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "nerve_network",
"field": "inputSchema.properties.target"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "target"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"target\" on \"nerve_storage\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"nerve_storage\" takes a URL/host parameter \"target\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "nerve_storage",
"field": "inputSchema.properties.target"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "target"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"nerve_lldb\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"nerve_lldb\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "nerve_lldb",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"nerve_sequence\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"nerve_sequence\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "nerve_sequence",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"nerve_lldb\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"nerve_lldb\" 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": "nerve_lldb"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"nerve_sequence\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"nerve_sequence\" 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": "nerve_sequence"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"nerve_storage\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"nerve_storage\" takes a path parameter \"path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "nerve_storage",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"nerve_storage"
],
"sensitiveSource": [
"nerve_tree",
"nerve_storage"
],
"externalSink": [
"nerve_network",
"nerve_lldb",
"nerve_sequence"
],
"selfContained": false,
"path": [
"nerve_storage",
"nerve_tree",
"nerve_lldb"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: nerve_storage → nerve_tree → nerve_lldb."
}
],
"capabilities": [
{
"tool": "nerve_view",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_tree",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"dump\""
]
}
},
{
"tool": "nerve_inspect",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_tap",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_scroll",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_swipe",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_double_tap",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_drag_drop",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_pull_to_refresh",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_pinch",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_context_menu",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_long_press",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_type",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_back",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_dismiss",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_console",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_network",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"http_request\""
]
}
},
{
"tool": "nerve_heap",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_storage",
"tags": [
"untrusted-input",
"sensitive-source"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
],
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "nerve_status",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_map",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_navigate",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_action",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_scroll_to_find",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_wait_idle",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_build",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_run",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_deeplink",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_grant_permissions",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_list_simulators",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_boot_simulator",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_appearance",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_run_device",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_list_devices",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_trace",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_highlight",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_modify",
"tags": [],
"reasons": {}
},
{
"tool": "nerve_lldb",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "nerve_sequence",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
}
],
"surfaceDigest": "6c603fa963afb5cc854f003e2ab2aed836383ba439c6e54688a2c5478b5f03ea",
"stats": {
"tools": 40,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 3,
"medium": 4,
"low": 3,
"info": 0
}
}
}