Paper Search Cli — the complete, unedited output of the deterministic mcptrustchecker engine v1.5.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.5.0",
"methodologyVersion": "mcptrustchecker-1.4"
},
"target": {
"id": "paper-search-cli",
"source": {
"kind": "package",
"origin": "paper-search-cli"
},
"server": {
"name": "paper-search-cli"
}
},
"grade": "A",
"score": {
"score": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.4"
},
"capability": {
"level": "moderate",
"reasons": [
"can send data / act on an external service"
],
"tags": [
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/platforms/ArxivSearcher.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/platforms/ArxivSearcher.js:269`): 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/platforms/ArxivSearcher.js"
},
"evidence": "axios.get('https://arxiv.org/search/'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/platforms/ArxivSearcher.js",
"line": 269
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/platforms/PMCSearcher.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/platforms/PMCSearcher.js:119`): 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/platforms/PMCSearcher.js"
},
"evidence": "axios.get('https://www.ebi.ac.uk/europepmc/webservices/rest/search'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/platforms/PMCSearcher.js",
"line": 119
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/platforms/ScopusSearcher.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/platforms/ScopusSearcher.js:280`): 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/platforms/ScopusSearcher.js"
},
"evidence": "axios.get(`https://api.elsevier.com/content/abstract/scopus_id/${scopusId}`",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/platforms/ScopusSearcher.js",
"line": 280
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "7572c28d96163ac8c41ccc368f73fbf081b0ed23ef96916dbe8796c7a894e974",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 3,
"low": 0,
"info": 0
}
}
}