Ai4scholar — 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": "ai4scholar-mcp",
"source": {
"kind": "package",
"origin": "ai4scholar-mcp"
},
"server": {
"name": "ai4scholar-mcp"
}
},
"grade": "A",
"score": {
"score": 95,
"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": "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-1.13"
},
"capability": {
"level": "moderate",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)"
],
"tags": [
"untrusted-input"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (28 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 in packaging/dev tooling (tests/test_biorxiv.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_biorxiv.py:9`): 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": "tests/test_biorxiv.py"
},
"evidence": "try: response = requests.get(\"https://api.biorxiv.org/details/biorxiv/0/1\", timeout=5) return response.s",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_biorxiv.py",
"line": 9,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_crossref.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_crossref.py: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": "tests/test_crossref.py"
},
"evidence": "try: response = requests.get(\"https://api.crossref.org/works?sample=1\", timeout=5) return response.statu",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_crossref.py",
"line": 11,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_google_scholar.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_google_scholar.py:9`): 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": "tests/test_google_scholar.py"
},
"evidence": "try: response = requests.get(\"https://scholar.google.com\", timeout=5) return response.status_code == 200",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_google_scholar.py",
"line": 9,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_iacr.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_iacr.py:10`): 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": "tests/test_iacr.py"
},
"evidence": "try: response = requests.get(\"https://eprint.iacr.org\", timeout=5) return response.status_code == 200",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_iacr.py",
"line": 10,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_medrxiv.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_medrxiv.py:9`): 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": "tests/test_medrxiv.py"
},
"evidence": "try: response = requests.get(\"https://api.medRxiv.org/details/medrxiv/0/1\", timeout=5) return response.s",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_medrxiv.py",
"line": 9,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_sci_hub.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_sci_hub.py: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": "tests/test_sci_hub.py"
},
"evidence": "onds response = requests.get(\"https://sci-hub.se\", timeout=10) return response.status_code == 200 ex",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_sci_hub.py",
"line": 14,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_semantic.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_semantic.py:12`): 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": "tests/test_semantic.py"
},
"evidence": "e {} response = requests.get(\"https://ai4scholar.net/graph/v1/paper/5bbfdf2e62f0508c65ba6de9c72fe2066fd98138\", h",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_semantic.py",
"line": 12,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"ai4scholar-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "ai4scholar-mcp"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"ai4scholar-mcp\" 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": "ai4scholar-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "search_arxiv",
"tags": [],
"reasons": {}
},
{
"tool": "search_pubmed",
"tags": [],
"reasons": {}
},
{
"tool": "get_pubmed_paper_detail",
"tags": [],
"reasons": {}
},
{
"tool": "search_biorxiv",
"tags": [],
"reasons": {}
},
{
"tool": "search_medrxiv",
"tags": [],
"reasons": {}
},
{
"tool": "search_google_scholar",
"tags": [],
"reasons": {}
},
{
"tool": "download_arxiv",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "download_biorxiv",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "download_medrxiv",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "download_pdf_by_doi",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "read_arxiv_paper",
"tags": [],
"reasons": {}
},
{
"tool": "read_biorxiv_paper",
"tags": [],
"reasons": {}
},
{
"tool": "read_medrxiv_paper",
"tags": [],
"reasons": {}
},
{
"tool": "search_semantic",
"tags": [],
"reasons": {}
},
{
"tool": "download_semantic",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "read_semantic_paper",
"tags": [],
"reasons": {}
},
{
"tool": "get_semantic_citations",
"tags": [],
"reasons": {}
},
{
"tool": "get_semantic_references",
"tags": [],
"reasons": {}
},
{
"tool": "search_semantic_authors",
"tags": [],
"reasons": {}
},
{
"tool": "get_semantic_author_papers",
"tags": [],
"reasons": {}
},
{
"tool": "get_semantic_recommendations",
"tags": [],
"reasons": {}
},
{
"tool": "get_semantic_recommendations_for_paper",
"tags": [],
"reasons": {}
},
{
"tool": "search_semantic_snippets",
"tags": [],
"reasons": {}
},
{
"tool": "get_pubmed_citations",
"tags": [],
"reasons": {}
},
{
"tool": "get_pubmed_related",
"tags": [],
"reasons": {}
},
{
"tool": "auto_cite",
"tags": [],
"reasons": {}
},
{
"tool": "nano_generate",
"tags": [],
"reasons": {}
},
{
"tool": "nano_edit",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "ef65c2cc6a9f61ca437f05403c547b95da9b853afd0b61f77d9b0320de3f09e1",
"stats": {
"tools": 28,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 0,
"low": 7,
"info": 2
}
}
}