scholar-mcp@0.11.0
VERIFIED· not startedPublisher claims: "Scholar MCP: multi-source academic search, citation traversal, and deep research" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
ADS_API_TOKENCORE_API_KEYCOURTLISTENER_API_TOKENDASHSCOPE_API_KEYEXA_API_KEYLENS_API_TOKENNCBI_API_KEYOPENAIRE_CLIENT_SECRETOPENALEX_API_KEYOPENALEX_API_KEYSS2_API_KEYS2_API_KEYSSCHOLAR_RERANK_API_KEYSCOPUS_API_KEYSPRINGER_API_KEYWOS_API_KEYConfiguration, not credentials: CLINE_MCP_SETTINGS_PATH, CODEX_HOME, COPILOT_HOME, DASHSCOPE_HTTP_BASE_URL, HF_ENDPOINT, LIBRARY_PROXY_BASE, LIBRARY_PROXY_COOKIE, LIBRARY_PROXY_COOKIES, LIBRARY_PROXY_PREFIX, MIMOCODE_CONFIG, MIMOCODE_CONFIG_DIR, MIMOCODE_HOME, OPENAIRE_CLIENT_ID, OPENALEX_EMAIL, OPENALEX_EMAILS, S2_RECOMMEND_POOL, S2_TIMEOUT, SCHOLAR_ACCESS_COMMAND, SCHOLAR_DATA_DIR, SCHOLAR_DOWNLOAD_DIR, SCHOLAR_GOOGLE_PROXY, SCHOLAR_IDLE_EXIT, SCHOLAR_KB_DIR, SCHOLAR_MCP_EXTENSIONS- Where it talks to
- semanticscholar.org (its own)Also doi.org, arxiv.org, openalex.org, elsevier.com, nih.gov, zenodo.org, aliyuncs.com, huggingface.co, creativecommons.org, hf-mirror.com, mksa.top, sci-hub.se, sci-hub.st, science.org, nature.com, springer.com, acm.org, wiley.com, unpaywall.org, biorxiv.org, medrxiv.org, ssrn.com, osf.io, chemrxiv.org, preprints.org, uniprot.org, harvard.edu, nii.ac.jp, core.ac.uk — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names doi.org, arxiv.org, openalex.org, elsevier.com, nih.gov, zenodo.org, aliyuncs.com, huggingface.co, creativecommons.org, hf-mirror.com, mksa.top, sci-hub.se, sci-hub.st, science.org, nature.com, springer.com, acm.org, wiley.com, unpaywall.org, biorxiv.org, medrxiv.org, ssrn.com, osf.io, chemrxiv.org, preprints.org, uniprot.org, harvard.edu, nii.ac.jp, core.ac.uk as well as its own vendor. The guard injects ADS_API_TOKEN, CORE_API_KEY, COURTLISTENER_API_TOKEN, DASHSCOPE_API_KEY, EXA_API_KEY, LENS_API_TOKEN, NCBI_API_KEY, OPENAIRE_CLIENT_SECRET, OPENALEX_API_KEY, OPENALEX_API_KEYS, S2_API_KEY, S2_API_KEYS, SCHOLAR_RERANK_API_KEY, SCOPUS_API_KEY, SPRINGER_API_KEY, WOS_API_KEY only into requests to semanticscholar.org (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-16 and scored it 88/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
tracked = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.writers = [subprocess.Popen([sys.executable, "-c", script, str(record_to.parent.parent), f"p{n}"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(command, input=json.dumps({**request, 'timeout': remaining}).encode('utf-8'),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.first = subprocess.check_output([sys.executable, '-c', script, str(tmp_path), 'online'], text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.restarted = subprocess.check_output([sys.executable, '-c', script, str(tmp_path), 'offline'], text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(["sh", str(ROOT / "scripts/launch.sh"), "sources", "--query", "a query with spaces"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["/usr/bin/security", "-i"], input=command, text=True, timeout=5,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(["/usr/bin/security", "find-generic-password", "-s", service,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run([binary, *args], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.completed = subprocess.run(command, capture_output=True, text=True, encoding='utf-8', errors='replace')Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.SCIHUB_MIRRORS = ["https://sci-hub.mksa.top", "https://sci-hub.se", "https://sci-hub.st"]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.result = subprocess.run([shutil.which("sh"), str(ROOT / "scripts/launch.sh"), "--help"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run([sys.executable, '-c', code], cwd=ROOT, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen([sys.executable, '-c', PROCESS, str(tmp_path)], cwd=ROOT,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for scholar-mcp@0.11.0 as of 48 min ago. This is the package itself, not its dependencies.