Meganova — 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": "meganova-mcp-server",
"source": {
"kind": "package",
"origin": "meganova-mcp-server"
},
"server": {
"name": "meganova-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": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (46 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-004",
"title": "Sensitive-source and external-sink co-exist",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tools that read sensitive data ([mesh_cost_summary]) and tools that can send data out ([mesh_eval_run, mesh_eval_history, mesh_eval_opt]) are exposed together. An agent can move private data to the sink.",
"remediation": "Keep secret-reading and egress capabilities on separate, separately-approved servers.",
"location": {
"kind": "flow",
"name": "mesh_cost_summary → mesh_eval_run"
},
"evidence": "sources [mesh_cost_summary] → sinks [mesh_eval_run, mesh_eval_history, mesh_eval_opt]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"mesh_cost_summary"
],
"sinks": [
"mesh_eval_run",
"mesh_eval_history",
"mesh_eval_opt"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"mesh_eval_run\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"mesh_eval_run\" 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": "mesh_eval_run"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"mesh_eval_history\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"mesh_eval_history\" 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": "mesh_eval_history"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"mesh_eval_opt\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"mesh_eval_opt\" 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": "mesh_eval_opt"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"mesh_eval_run\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"mesh_eval_run\" 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": "mesh_eval_run"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"mesh_eval_history\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"mesh_eval_history\" 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": "mesh_eval_history"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"mesh_eval_opt\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"mesh_eval_opt\" 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": "mesh_eval_opt"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"meganova-mcp-server\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "meganova-mcp-server"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"meganova-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": "meganova-mcp-server"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"mesh_cost_summary"
],
"externalSink": [
"mesh_eval_run",
"mesh_eval_history",
"mesh_eval_opt"
],
"selfContained": false,
"path": [
"mesh_cost_summary",
"mesh_eval_history"
],
"pathWired": false,
"description": "A sensitive-source → external-sink chain exists: mesh_cost_summary → mesh_eval_history."
}
],
"capabilities": [
{
"tool": "mesh_list_agents",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_get_agent",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_register_agent",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_update_agent",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_delete_agent",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_agent_tools",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_agent_memory",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_clear_agent_memory",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_agent_think_log",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_delegate_task",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_agent_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_save_session",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_restore_session",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_reload_skill",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_agent_checkpoint",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_agent_info",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_agent_chat",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_agent_confirm_tool",
"tags": [],
"reasons": {}
},
{
"tool": "chat_completion",
"tags": [],
"reasons": {}
},
{
"tool": "create_embeddings",
"tags": [],
"reasons": {}
},
{
"tool": "rerank_documents",
"tags": [],
"reasons": {}
},
{
"tool": "generate_image",
"tags": [],
"reasons": {}
},
{
"tool": "generate_video",
"tags": [],
"reasons": {}
},
{
"tool": "transcribe_audio",
"tags": [],
"reasons": {}
},
{
"tool": "list_models",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_call_log",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_call_summary",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_traces",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_metrics",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_cost_summary",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_token\""
]
}
},
{
"tool": "mesh_graph",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_request_journey",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_health",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_eval_run",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "mesh_eval_history",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "mesh_route",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_route_and_execute",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_chat",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_eval_opt",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "mesh_harness",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_delegation_status",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_route_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_list_skills",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_list_presets",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_search_catalog",
"tags": [],
"reasons": {}
},
{
"tool": "mesh_sync_catalog",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "f2427e2e19c4e98ecb4a50cee1774439a5ece8be508ed5bfc6e1af4812b0e83d",
"stats": {
"tools": 46,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 3,
"info": 2
}
}
}