台灣健康資訊 MCP server
com.penguindriver/healthpenguindriver.comstreamable-httpv1.0.1Scanned
台灣健康資訊:篩檢、慢性病與飲食等健康資訊整理。台灣繁體中文 MCP 工具。
10 tools: 5 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 10
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the 台灣健康資訊 MCP server can do
The 台灣健康資訊 MCP server is published by penguindriver.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (5 tools: check_meal_cancer_risk, check_cancer_screening_eligibility, check_home_blood_pressure, check_blood_glucose and 1 more), but cannot delete data. 5 tools only read.
10 tools bring in text other people can write (get_counseling_guide, get_glp1_side_effects, check_meal_cancer_risk and 7 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Changes things 5Claude Code: ask
check_blood_glucose判讀單次血糖值(mg/dL),when 為 fasting(飯前)或 after_meal(飯後),回傳是否在一般控制目標內與低血糖處理。Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 判讀單次血糖值(mg/dL),when 為 fasting(飯前)或 after_meal(飯後),回傳是否在一般控制目標內與低血糖處理。
Annotations the server declares
- title: 判讀單次血糖值
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_cancer_screening_eligibility依年齡、性別、吸菸、嚼檳榔、家族史,列出台灣 115 年可做的公費癌症篩檢(子宮頸、乳、大腸、胃、口腔、肺)。Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 依年齡、性別、吸菸、嚼檳榔、家族史,列出台灣 115 年可做的公費癌症篩檢(子宮頸、乳、大腸、胃、口腔、肺)。
Annotations the server declares
- title: 依年齡、性別、吸菸、嚼檳榔、家族史
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_home_blood_pressure判讀居家血壓(依台灣 2022 高血壓指引 130/80),回傳平均、分級、是否達危急值與 722 量測方法。readings 例:128/82,134/86(最多 6 筆)。Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 判讀居家血壓(依台灣 2022 高血壓指引 130/80),回傳平均、分級、是否達危急值與 722 量測方法。readings 例:128/82,134/86(最多 6 筆)。
Annotations the server declares
- title: 判讀居家血壓
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_meal_cancer_risk輸入一餐或一天吃的東西(中文),比對 IARC 致癌分級與防癌飲食建議,列出加工肉品、紅肉、酒精、檳榔等風險項目與改善建議。Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 輸入一餐或一天吃的東西(中文),比對 IARC 致癌分級與防癌飲食建議,列出加工肉品、紅肉、酒精、檳榔等風險項目與改善建議。
Annotations the server declares
- title: 輸入一餐或一天吃的東西
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_product_safety一次比對藥品回收、違規食品廣告、國際食品警訊三個資料集,檢查某產品或品牌有沒有紀錄。Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 一次比對藥品回收、違規食品廣告、國際食品警訊三個資料集,檢查某產品或品牌有沒有紀錄。
Annotations the server declares
- title: 一次比對藥品回收、違規食品廣告、國際食品警訊三個資料集
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 5Show 5 read-only tools
get_counseling_guide台灣線上(通訊)心理諮商的合法條件、18 歲限制、15–45 歲免費 3 次心理諮商方案、預約步驟與 1925 等危機專線。Reads text others writeNo findings
Why it is in this group
- The name "get_counseling_guide" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 台灣線上(通訊)心理諮商的合法條件、18 歲限制、15–45 歲免費 3 次心理諮商方案、預約步驟與 1925 等危機專線。
Annotations the server declares
- title: 台灣線上
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_drug_recalls查詢台灣食藥署公告的藥品回收(品名、批號、回收分級、原因)。使用者問「這個藥有沒有被回收」時使用。Reads text others writeNo findings
Why it is in this group
- The name "get_drug_recalls" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 查詢台灣食藥署公告的藥品回收(品名、批號、回收分級、原因)。使用者問「這個藥有沒有被回收」時使用。
Annotations the server declares
- title: 查詢台灣食藥署公告的藥品回收
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_food_ad_violations查詢台灣食藥署公布的違規食品廣告(誇大療效等)。使用者問「這個保健食品廣告合法嗎」時使用。Reads text others writeNo findings
Why it is in this group
- The name "get_food_ad_violations" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 查詢台灣食藥署公布的違規食品廣告(誇大療效等)。使用者問「這個保健食品廣告合法嗎」時使用。
Annotations the server declares
- title: 查詢台灣食藥署公布的違規食品廣告
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_glp1_side_effects台灣核准的 GLP-1 減重藥(猛健樂 tirzepatide、週纖達 semaglutide、善纖達 liraglutide)副作用發生率、嚴重警訊、何時就醫、食藥署提醒。不提供劑量建議。Reads text others writeNo findings
Why it is in this group
- The name "get_glp1_side_effects" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 台灣核准的 GLP-1 減重藥(猛健樂 tirzepatide、週纖達 semaglutide、善纖達 liraglutide)副作用發生率、嚴重警訊、何時就醫、食藥署提醒。不提供劑量建議。
Annotations the server declares
- title: 台灣核准的 GLP-1 減重藥
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_international_food_alerts查詢食藥署整理的國際食品安全警訊(各國回收、下架)。Reads text others writeNo findings
Why it is in this group
- The name "get_international_food_alerts" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 查詢食藥署整理的國際食品安全警訊(各國回收、下架)。
Annotations the server declares
- title: 查詢食藥署整理的國際食品安全警訊
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write10
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:25 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://health.penguindriver.com/mcp: tools/list returned 10 tools to an anonymous client, including check_meal_cancer_risk (write), check_cancer_screening_eligibility (write), check_home_blood_pressure (write), check_blood_glucose (write), check_product_safety (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools10 changed.~10 changedView diff
- Changed:check_blood_glucoseChanges thingstitleannotations
- Changed:check_cancer_screening_eligibilityChanges thingstitleannotations
- Changed:check_home_blood_pressureChanges thingstitleannotations
- Changed:check_meal_cancer_riskChanges thingstitleannotations
- Changed:check_product_safetyChanges thingstitleannotations
- Changed:get_counseling_guideOnly readstitleannotations
- Changed:get_drug_recallsOnly readstitleannotations
- Changed:get_food_ad_violationsOnly readstitleannotations
- Changed:get_glp1_side_effectsOnly readstitleannotations
- Changed:get_international_food_alertsOnly readstitleannotations
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http health https://health.penguindriver.com/mcpclaude mcp add --transport http health https://health.penguindriver.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__health__get_counseling_guide",
"mcp__health__get_glp1_side_effects",
"mcp__health__get_drug_recalls",
"mcp__health__get_food_ad_violations",
"mcp__health__get_international_food_alerts"
],
"ask": [
"mcp__health__check_meal_cancer_risk",
"mcp__health__check_cancer_screening_eligibility",
"mcp__health__check_home_blood_pressure",
"mcp__health__check_blood_glucose",
"mcp__health__check_product_safety"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as health. Review it before you use it.
Capability tags behind 10 rules
- mcp__health__get_counseling_guide untrusted-input
- mcp__health__get_glp1_side_effects untrusted-input
- mcp__health__check_meal_cancer_risk untrusted-input
- mcp__health__check_cancer_screening_eligibility untrusted-input
- mcp__health__check_home_blood_pressure untrusted-input
- mcp__health__check_blood_glucose untrusted-input
- mcp__health__get_drug_recalls untrusted-input
- mcp__health__get_food_ad_violations untrusted-input
- mcp__health__get_international_food_alerts untrusted-input
- mcp__health__check_product_safety untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.penguindriver/health/verify?hash=f5007145632ceffaac7f18e17e766dcf23c11f54cb6eb06dd6485d13586523b3" | jq -e '.changed == false'Pinned hash f5007145632c, from Nov 18, 2026, 20:19 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.penguindriver/health/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.penguindriver/health)Source: MCP Registry · repository. Synced Nov 18, 2026, 20:17 UTC.
台灣健康資訊 MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the 台灣健康資訊 MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the 台灣健康資訊 MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the 台灣健康資訊 MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the 台灣健康資訊 MCP server have?
- 10 tools: 5 write, 5 read. check_meal_cancer_risk, check_cancer_screening_eligibility, check_home_blood_pressure, check_blood_glucose, check_product_safety, get_counseling_guide, get_glp1_side_effects, get_drug_recalls and 2 more.
Does the 台灣健康資訊 MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the 台灣健康資訊 MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the 台灣健康資訊 MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.