Playwright Mcp Server — 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": "https://nexgendata-mcp-proxy.steve-corbeil.workers.dev/playwright-mcp-server/mcp",
"source": {
"kind": "http",
"origin": "https://nexgendata-mcp-proxy.steve-corbeil.workers.dev/playwright-mcp-server/mcp"
},
"server": {
"name": "playwright-mcp-server",
"version": "2.14.7"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "coverage-honesty",
"level": "live",
"label": "inspection depth (live) — 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": "live",
"inputs": {
"toolSurface": true,
"implementationSource": false,
"packageMetadata": false,
"liveTransport": true
},
"caveats": []
},
"findings": [
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"evaluate\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"evaluate\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "evaluate"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"evaluate\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"evaluate\" takes a command-shaped parameter \"script\" 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": "evaluate",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"evaluate\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"evaluate\" 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": "evaluate"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-NET-005",
"title": "Remote HTTP MCP endpoint",
"category": "network",
"severity": "info",
"confidence": "strong",
"description": "Remote endpoint nexgendata-mcp-proxy.steve-corbeil.workers.dev. MCP Trust Checker does not test server-side authentication/authorization; verify the endpoint requires auth.",
"location": {
"kind": "transport"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "navigate",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "click",
"tags": [],
"reasons": {}
},
{
"tool": "type_text",
"tags": [],
"reasons": {}
},
{
"tool": "get_text",
"tags": [],
"reasons": {}
},
{
"tool": "get_html",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "select_option",
"tags": [],
"reasons": {}
},
{
"tool": "scroll",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for",
"tags": [],
"reasons": {}
},
{
"tool": "get_links",
"tags": [],
"reasons": {}
},
{
"tool": "extract_table",
"tags": [],
"reasons": {}
},
{
"tool": "page_pdf",
"tags": [],
"reasons": {}
},
{
"tool": "fill_form",
"tags": [],
"reasons": {}
},
{
"tool": "get_cookies",
"tags": [],
"reasons": {}
},
{
"tool": "set_cookies",
"tags": [],
"reasons": {}
},
{
"tool": "close_browser",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "7f1f6d2c79c552a7b5e95683bdf244fe3ef26843bcf75ef352a13f2df0279b25",
"stats": {
"tools": 17,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 1,
"low": 1,
"info": 1
}
}
}