Academic Search (PyPI) MCP Server
academic-search-mcp
PyPI
v0.1.8
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 8 = 92. 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 |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 11
high Shell/command execution in server code (paper_search_mcp/pdf_utils.py)MTC-SRC-002
In the server's implementation (`paper_search_mcp/pdf_utils.py:40`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: oding result = subprocess.run( ['pdftotext', '-layout', '-enc', 'UTF-8', pdf_path, '-'],
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 paper_search_mcp/pdf_utils.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_biorxiv.py)MTC-SRC-003
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.
Evidence: ry: response = requests.get("https://api.biorxiv.org/details/biorxiv/0/1", timeout=5) return response.
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
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_core.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_core.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: ry: response = requests.get( "https://api.core.ac.uk/v3/search/works", params={"q": "
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_core.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_crossref.py)MTC-SRC-003
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.
Evidence: ry: response = requests.get("https://api.crossref.org/works?sample=1", timeout=5) return response.stat
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
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_cyberleninka.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_cyberleninka.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: ry: response = requests.get( "https://cyberleninka.ru", impersonate="chrome",
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_cyberleninka.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_google_scholar.py)MTC-SRC-003
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.
Evidence: ry: response = requests.get("https://scholar.google.com", timeout=5) return response.status_code == 20
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
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_iacr.py)MTC-SRC-003
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.
Evidence: ry: response = requests.get("https://eprint.iacr.org", timeout=5) return response.status_code == 200
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
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_medrxiv.py)MTC-SRC-003
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.
Evidence: ry: response = requests.get("https://api.medRxiv.org/details/medrxiv/0/1", timeout=5) return response.
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
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_sci_hub.py)MTC-SRC-003
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.
Evidence: nds response = requests.get("https://sci-hub.se", timeout=10) return response.status_code == 200
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
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_semantic.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_semantic.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: ry: response = requests.get("https://api.semanticscholar.org/graph/v1/paper/5bbfdf2e62f0508c65ba6de9c72fe2066fd
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 Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_ssrn.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_ssrn.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: ry: response = requests.get( "https://papers.ssrn.com", impersonate="chrome",
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_ssrn.py
Tools 21
Each tool and what it can reach — statically extracted from the published source.
download_paperingests untrusted inputget_author_papersno sensitive capabilityget_crossref_paper_by_doino sensitive capabilityget_openalex_citationsno sensitive capabilityget_openalex_referencesno sensitive capabilityget_openalex_work_by_idno sensitive capabilityget_paper_by_doino sensitive capabilityread_paperno sensitive capabilitysearch_arxivno sensitive capabilitysearch_authorsno sensitive capability
Show 11 more tools ↓
search_biorxivno sensitive capabilitysearch_coreno sensitive capabilitysearch_crossrefno sensitive capabilitysearch_cyberleninkano sensitive capabilitysearch_google_scholarno sensitive capabilitysearch_iacrno sensitive capabilitysearch_medrxivno sensitive capabilitysearch_openalexno sensitive capabilitysearch_pubmedno sensitive capabilitysearch_semanticno sensitive capabilitysearch_ssrnno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (21 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 1
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 |
|---|---|---|---|---|
v0.1.8 latest |
A 92/100 | 11 | 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 academic-search-mcp --online --registry pypiOther implementations of Academic Search 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More 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.