taiwan-laboratory-mcp@0.1.3
CAUTION· not startedPublisher claims: "MCP server exposing Taiwan laboratory medicine public data as AI-agent tools." 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: Caution 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
TAIWAN_LAB_HTTP_BEARER_TOKEN_SHA256Configuration, not credentials: CONFIG_PATH, DATA_DIR, MCP_EXE, TAIWAN_LAB_DATA_DIR, TAIWAN_LAB_DATA_MODE, TAIWAN_LAB_HTTP_ALLOWED_HOSTS, TAIWAN_LAB_HTTP_HOST, TAIWAN_LAB_HTTP_PATH, TAIWAN_LAB_HTTP_PORT, TAIWAN_LAB_HTTP_USAGE_LOG- Where it talks to
- no vendor host named in the codeAlso cdc.gov.tw, data.gov.tw, astral.sh, nhi.gov.tw, fda.gov.tw — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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 cdc.gov.tw, data.gov.tw, astral.sh, nhi.gov.tw, fda.gov.tw as well as its own vendor. The guard injects TAIWAN_LAB_HTTP_BEARER_TOKEN_SHA256 only into requests to the host you bind (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 2026-11-19 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Privileged sudo command; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
|| stop_with_advice '自動安裝 uv 失敗' '開一個新的終端機視窗,貼上 curl -LsSf https://astral.sh/uv/install.sh | sh,裝完再跑一次這支腳本。'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.sudo chown "$(id -u):$(id -g)" "$backup"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chmod 700 "$recovery_dir"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.from .tfda_autoupdate import plan_tfda_retentionFix: Pin versions and sources; vendor anything fetched at install time.chmod 700 "${base}/grok-production-supervise-app.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.sudo install -o root -g root -m 755 "$patch_file" "$vendor_launcher"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.|| stop_with_advice '自動安裝 uv 失敗' '開一個新的終端機視窗,貼上 curl -LsSf https://astral.sh/uv/install.sh | sh,裝完再跑一次這支腳本。'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.curl -LsSf https://astral.sh/uv/install.sh | sh >/dev/null 2>&1 \Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.curl -LsSf https://astral.sh/uv/install.sh | sh >/dev/null 2>&1 \Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.sudo grep -Fq "$end_marker" "$vendor_launcher"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.sudo cp "$vendor_launcher" "$backup"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.sudo chown "$(id -u):$(id -g)" "$backup"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if ! sudo grep -Fq "$begin_marker" "$vendor_launcher"; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod 700 "$supervisor_next"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chmod 600 "$backup"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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 taiwan-laboratory-mcp@0.1.3 as of 16 h ago. This is the package itself, not its dependencies.
What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim masalu0105-gif: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.