Fathom Fyi — 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": "fathom-fyi",
"source": {
"kind": "package",
"origin": "fathom-fyi"
},
"server": {
"name": "fathom-fyi"
}
},
"grade": "A",
"score": {
"score": 96,
"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": "moderate",
"label": "capability blast radius (moderate) — client exposure if the model is manipulated",
"appliedPenalty": 3
},
{
"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": "moderate",
"reasons": [
"can send data / act on an external service"
],
"tags": [
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (32 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-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/auth/tier-check.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/auth/tier-check.js:68`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/auth/tier-check.js"
},
"evidence": "const res = await fetch('https://fathom.fyi/api/verify', { headers: { 'x-fathom-key': apiKey },",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/auth/tier-check.js",
"line": 68,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/sources/defillama.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/sources/defillama.js:28`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/sources/defillama.js"
},
"evidence": "{ const res = await fetch('https://api.llama.fi/summary/fees', { headers: { Accept: 'application/json' },",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/sources/defillama.js",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/sources/weather.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/sources/weather.js:13`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/sources/weather.js"
},
"evidence": "const res = await fetch(`https://api.open-meteo.com/v1/forecast?latitude=${center.lat}&longitude=${center.lon}&cur",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/sources/weather.js",
"line": 13,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/tools/rotate-api-key.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/rotate-api-key.js:14`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/tools/rotate-api-key.js"
},
"evidence": "const res = await fetch('https://fathom.fyi/api/rotate-key', { method: 'POST', headers: {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/tools/rotate-api-key.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/worker/webhook-manager.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/worker/webhook-manager.js:11`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/worker/webhook-manager.js"
},
"evidence": "try { await fetch('https://fathom.fyi/api/kv', { method: 'POST', headers: { 'Content",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/worker/webhook-manager.js",
"line": 11,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "get_market_regime",
"tags": [],
"reasons": {}
},
{
"tool": "get_sentiment_state",
"tags": [],
"reasons": {}
},
{
"tool": "get_narrative_pulse",
"tags": [],
"reasons": {}
},
{
"tool": "get_asset_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_temporal_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_defi_health",
"tags": [],
"reasons": {}
},
{
"tool": "get_macro_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_onchain_pulse",
"tags": [],
"reasons": {}
},
{
"tool": "get_reality_check",
"tags": [],
"reasons": {}
},
{
"tool": "set_portfolio_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_portfolio_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "get_crowd_intelligence",
"tags": [],
"reasons": {}
},
{
"tool": "get_signal_history",
"tags": [],
"reasons": {}
},
{
"tool": "set_alert",
"tags": [],
"reasons": {}
},
{
"tool": "get_alerts",
"tags": [],
"reasons": {}
},
{
"tool": "get_watchlist_report",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate_strategy",
"tags": [],
"reasons": {}
},
{
"tool": "set_custom_strategy",
"tags": [],
"reasons": {}
},
{
"tool": "get_chain_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_historical_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_alternative_signals",
"tags": [],
"reasons": {}
},
{
"tool": "set_signal_preferences",
"tags": [],
"reasons": {}
},
{
"tool": "get_account_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_question_context",
"tags": [],
"reasons": {}
},
{
"tool": "set_webhook",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
]
}
},
{
"tool": "manage_webhooks",
"tags": [],
"reasons": {}
},
{
"tool": "get_derivatives_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_stablecoin_flows",
"tags": [],
"reasons": {}
},
{
"tool": "get_correlation_matrix",
"tags": [],
"reasons": {}
},
{
"tool": "rotate_api_key",
"tags": [],
"reasons": {}
},
{
"tool": "get_asset_momentum",
"tags": [],
"reasons": {}
},
{
"tool": "get_event_catalyst_timeline",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "230f8a9ad11048ffedfce08661a807a9b85acba747e71fd792006c8d95cfd917",
"stats": {
"tools": 32,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 5,
"low": 0,
"info": 0
}
}
}