A2amarket — 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": "@hz-abyssal-heart/a2amarket-mcp-server",
"source": {
"kind": "package",
"origin": "@hz-abyssal-heart/a2amarket-mcp-server"
},
"server": {
"name": "@hz-abyssal-heart/a2amarket-mcp-server"
}
},
"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 send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)"
],
"tags": [
"external-sink",
"sensitive-source"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (51 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-003",
"title": "Read-and-egress in one tool: \"register_agent\"",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tool \"register_agent\" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.",
"remediation": "Separate reading from sending; require explicit user confirmation before egress of file/secret contents.",
"location": {
"kind": "flow",
"name": "register_agent"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"tags": [
"external-sink",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-FLOW-003",
"title": "Read-and-egress in one tool: \"update_agent\"",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tool \"update_agent\" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.",
"remediation": "Separate reading from sending; require explicit user confirmation before egress of file/secret contents.",
"location": {
"kind": "flow",
"name": "update_agent"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"tags": [
"external-sink",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-FLOW-004",
"title": "Sensitive-source and external-sink co-exist",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tools that read sensitive data ([register_agent, update_agent]) and tools that can send data out ([register_agent, send_message, update_agent]) 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": "register_agent → send_message"
},
"evidence": "sources [register_agent, update_agent] → sinks [register_agent, send_message, update_agent]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"register_agent",
"update_agent"
],
"sinks": [
"register_agent",
"send_message",
"update_agent"
]
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"endpoint_url\" on \"register_agent\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"register_agent\" takes a URL/host parameter \"endpoint_url\" 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": "register_agent",
"field": "inputSchema.properties.endpoint_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "endpoint_url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"webhook_url\" on \"register_agent\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"register_agent\" takes a URL/host parameter \"webhook_url\" 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": "register_agent",
"field": "inputSchema.properties.webhook_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "webhook_url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"webhook_url\" on \"update_agent\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"update_agent\" takes a URL/host parameter \"webhook_url\" 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": "update_agent",
"field": "inputSchema.properties.webhook_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "webhook_url"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"register_agent"
],
"externalSink": [
"register_agent"
],
"selfContained": true,
"description": "Tool \"register_agent\" both reads sensitive data and can send it externally."
},
{
"id": "flow-2",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"update_agent"
],
"externalSink": [
"update_agent"
],
"selfContained": true,
"description": "Tool \"update_agent\" both reads sensitive data and can send it externally."
},
{
"id": "flow-3",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"register_agent",
"update_agent"
],
"externalSink": [
"register_agent",
"send_message",
"update_agent"
],
"selfContained": false,
"path": [
"register_agent",
"send_message"
],
"pathWired": true,
"description": "A sensitive-source → external-sink chain exists: register_agent ⇒ send_message."
}
],
"capabilities": [
{
"tool": "register_agent",
"tags": [
"external-sink",
"sensitive-source"
],
"reasons": {
"external-sink": [
"parameter \"webhook\""
],
"sensitive-source": [
"parameter \"secret\""
]
}
},
{
"tool": "get_profile",
"tags": [],
"reasons": {}
},
{
"tool": "update_profile",
"tags": [],
"reasons": {}
},
{
"tool": "search_agents",
"tags": [],
"reasons": {}
},
{
"tool": "verify_email",
"tags": [],
"reasons": {}
},
{
"tool": "check_handle",
"tags": [],
"reasons": {}
},
{
"tool": "get_my_agents",
"tags": [],
"reasons": {}
},
{
"tool": "list_api_keys",
"tags": [],
"reasons": {}
},
{
"tool": "get_usage",
"tags": [],
"reasons": {}
},
{
"tool": "rotate_api_key",
"tags": [],
"reasons": {}
},
{
"tool": "publish_intent",
"tags": [],
"reasons": {}
},
{
"tool": "get_intent_status",
"tags": [],
"reasons": {}
},
{
"tool": "cancel_intent",
"tags": [],
"reasons": {}
},
{
"tool": "get_sourcing_status",
"tags": [],
"reasons": {}
},
{
"tool": "list_matches",
"tags": [],
"reasons": {}
},
{
"tool": "list_responses",
"tags": [],
"reasons": {}
},
{
"tool": "select_and_negotiate",
"tags": [],
"reasons": {}
},
{
"tool": "get_negotiation_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_negotiation_rounds",
"tags": [],
"reasons": {}
},
{
"tool": "authorize_deal",
"tags": [],
"reasons": {}
},
{
"tool": "reject_deal",
"tags": [],
"reasons": {}
},
{
"tool": "get_order_status",
"tags": [],
"reasons": {}
},
{
"tool": "submit_offer",
"tags": [],
"reasons": {}
},
{
"tool": "accept_deal",
"tags": [],
"reasons": {}
},
{
"tool": "create_settlement",
"tags": [],
"reasons": {}
},
{
"tool": "set_preferences",
"tags": [],
"reasons": {}
},
{
"tool": "get_preferences",
"tags": [],
"reasons": {}
},
{
"tool": "declare_supply",
"tags": [],
"reasons": {}
},
{
"tool": "update_supply",
"tags": [],
"reasons": {}
},
{
"tool": "list_supply_products",
"tags": [],
"reasons": {}
},
{
"tool": "get_supply_product",
"tags": [],
"reasons": {}
},
{
"tool": "delete_supply_product",
"tags": [],
"reasons": {}
},
{
"tool": "respond_to_intent",
"tags": [],
"reasons": {}
},
{
"tool": "subscribe_intent",
"tags": [],
"reasons": {}
},
{
"tool": "unsubscribe_intent",
"tags": [],
"reasons": {}
},
{
"tool": "list_subscriptions",
"tags": [],
"reasons": {}
},
{
"tool": "get_incoming_intents",
"tags": [],
"reasons": {}
},
{
"tool": "set_hosted_strategy",
"tags": [],
"reasons": {}
},
{
"tool": "list_hosted_strategies",
"tags": [],
"reasons": {}
},
{
"tool": "delete_hosted_strategy",
"tags": [],
"reasons": {}
},
{
"tool": "get_reputation",
"tags": [],
"reasons": {}
},
{
"tool": "check_reputation",
"tags": [],
"reasons": {}
},
{
"tool": "get_balance",
"tags": [],
"reasons": {}
},
{
"tool": "send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "get_messages",
"tags": [],
"reasons": {}
},
{
"tool": "list_conversations",
"tags": [],
"reasons": {}
},
{
"tool": "get_conversation",
"tags": [],
"reasons": {}
},
{
"tool": "get_notifications",
"tags": [],
"reasons": {}
},
{
"tool": "mark_notification_read",
"tags": [],
"reasons": {}
},
{
"tool": "mark_all_notifications_read",
"tags": [],
"reasons": {}
},
{
"tool": "update_agent",
"tags": [
"external-sink",
"sensitive-source"
],
"reasons": {
"external-sink": [
"keyword \"webhook\"",
"parameter \"webhook\""
],
"sensitive-source": [
"parameter \"secret\""
]
}
}
],
"surfaceDigest": "e2244043ca04341db5ae552fa32ea9588dec973033e7845d6d9160b7490a68d1",
"stats": {
"tools": 51,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 3,
"low": 0,
"info": 0
}
}
}