Ai4scholar MCP Server
ai4scholar-mcp
PyPI
v0.4.0
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 2.1 = 98. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −2.1 | Package has no source repository MTC-SUP-011 | supply-chain |
2. Client adoption risk — 98 − 8 = 90. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
| −5 | publisher verification (unlocatable) — no provenance and no public repository to inspect |
| ✓ | inspection depth (source) — how much of the target the scan could see |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 8
medium Hardcoded egress to an external endpoint (tests/test_biorxiv.py)MTC-SRC-003
In the server's implementation (`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.
Evidence: requests.get("https://api.biorxiv.org/details/biorxiv/0/1"
Fix: 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: server tests/test_biorxiv.py
medium Hardcoded egress to an external endpoint (tests/test_crossref.py)MTC-SRC-003
In the server's implementation (`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.
Evidence: requests.get("https://api.crossref.org/works?sample=1"
Fix: 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: server tests/test_crossref.py
medium Hardcoded egress to an external endpoint (tests/test_google_scholar.py)MTC-SRC-003
In the server's implementation (`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.
Evidence: requests.get("https://scholar.google.com"
Fix: 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: server tests/test_google_scholar.py
medium Hardcoded egress to an external endpoint (tests/test_iacr.py)MTC-SRC-003
In the server's implementation (`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.
Evidence: requests.get("https://eprint.iacr.org"
Fix: 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: server tests/test_iacr.py
medium Hardcoded egress to an external endpoint (tests/test_medrxiv.py)MTC-SRC-003
In the server's implementation (`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.
Evidence: requests.get("https://api.medRxiv.org/details/medrxiv/0/1"
Fix: 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: server tests/test_medrxiv.py
medium Hardcoded egress to an external endpoint (tests/test_sci_hub.py)MTC-SRC-003
In the server's implementation (`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.
Evidence: requests.get("https://sci-hub.se"
Fix: 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: server tests/test_sci_hub.py
medium Hardcoded egress to an external endpoint (tests/test_semantic.py)MTC-SRC-003
In the server's implementation (`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.
Evidence: requests.get("https://ai4scholar.net/graph/v1/paper/5bbfdf2e62f0508c65ba6de9c72fe2066fd98138"
Fix: 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: server tests/test_semantic.py
low Package has no source repositoryMTC-SUP-011
"ai4scholar-mcp" declares no repository URL, so its published artifact cannot be compared against reviewable source.
Fix: Prefer packages that link to public, reviewable source.
Location: package ai4scholar-mcp
Tools 28
Each tool and what it can reach — statically extracted from the published source.
download_arxivingests untrusted inputdownload_biorxivingests untrusted inputdownload_medrxivingests untrusted inputdownload_pdf_by_doiingests untrusted inputdownload_semanticingests untrusted inputauto_citeno sensitive capabilityget_pubmed_citationsno sensitive capabilityget_pubmed_paper_detailno sensitive capabilityget_pubmed_relatedno sensitive capabilityget_semantic_author_papersno sensitive capabilityget_semantic_citationsno sensitive capabilityget_semantic_recommendationsno sensitive capabilityget_semantic_recommendations_for_paperno sensitive capabilityget_semantic_referencesno sensitive capabilitynano_editno sensitive capabilitynano_generateno sensitive capabilityread_arxiv_paperno sensitive capabilityread_biorxiv_paperno sensitive capabilityread_medrxiv_paperno sensitive capabilityread_semantic_paperno sensitive capabilitysearch_arxivno sensitive capabilitysearch_biorxivno sensitive capabilitysearch_google_scholarno sensitive capabilitysearch_medrxivno sensitive capabilitysearch_pubmedno sensitive capabilitysearch_semanticno sensitive capabilitysearch_semantic_authorsno sensitive capabilitysearch_semantic_snippetsno sensitive capability
What this scan could not see
- 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>".
Versions
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.4.0 latest |
A 90/100 | 8 | 1.8.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan ai4scholar-mcp --online --registry pypiMore in Learning & Documentation
Security scan results for the Agentmail MCP server.
Security scan results for the Alfahq MCP server.
Security scan results for the Alpine MCP server.
Security scan results for the Atag MCP server.
Security scan results for the Aurais Mcp Research Reader MCP server.
Security scan results for the Bookstack MCP server.