MCP servers › io.github.foxhsiao › roadsafety-mcp
MCP server · registry snapshot 2026-11-13 · last tested 2026-11-13
roadsafety-mcp MCP server
Registry name io.github.foxhsiao/roadsafety-mcp
Taiwan Road Safety Data (Unofficial) — the publisher's title
by foxhsiao · GitHub account (the registry's namespace rule)Website ↗
Unofficial. Taiwan road crash hotspots, school-zone crashes and speed-camera points (roadsafety.tw). — the publisher's description
Summary
io.github.foxhsiao/roadsafety-mcp is a remote MCP server listed in the official MCP registry at version 0.1.0, under the namespace of the GitHub account foxhsiao. On 2026-11-13 ProtocolProbe connected to it in read-only mode and read its inventory: 19 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 19
- Last tested
- 2026-11-13
Tool list size
8,441 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (19 tools). Counted with Anthropic's token counter on 2026-11-13, from the tool list we read on 2026-11-13. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-13 (roadsafety.taux.io), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (0.1.0).
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-13
- Mode
- read-only (no tool calls)
- Latest version
- 0.1.0, published 2026-11-13 (registry, as of the 2026-11-13 snapshot)
- First listed version
- 2026-11-13 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-11-13
- Package and repository
- checked 2026-11-13
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-11-12, listed on 2026-11-13 with version 0.1.0 (published 2026-11-13).
Source: the official MCP Registry list on 2026-11-12 and on 2026-11-13.
What it is
What does this server offer?
Observed inventoryNone of its 19 tools are described as changing anything. For 19 the reading was uncertain, so no mark is shown.
“確認 roadsafety MCP server 是否運作中,原樣回傳訊息”
1 input
messagestring
- get_cbi_hotspots
“查詢指定縣市(可再限定鄉鎮)的肇事熱點排名,資料來自交通部道安總動員”
5 inputs, 2 required
yearintegerrequired“民國年,106 起到今年,例如 114”monthstring“ALL 或 01–12”citystringrequired“縣市名稱,例如 屏東縣”areastring“ALL 或「縣市|鄉鎮」,例如 屏東縣|恆春鎮”metricstring“排名依據”
- get_hotspot_detail
“查詢單一肇事熱點的肇因與碰撞類型分布;hotspotKeyid 與 kind 取自 get_cbi_hotspots 的結果”
2 inputs, 2 required
kindstringrequired“熱點類型,取自 get_cbi_hotspots 的 kind”hotspotKeyidstringrequired“熱點代碼,取自 get_cbi_hotspots 的 hotspotKeyid”
- get_location_history
“查詢單一路口或路段歷年(106 年起)的事故件數、死亡與受傷人數趨勢;locationKeyid 與 kind 取自 get_cbi_hotspots 的結果”
2 inputs, 2 required
kindstringrequired“熱點類型,取自 get_cbi_hotspots 的 kind”locationKeyidstringrequired“地點代碼,取自 get_cbi_hotspots 的 locationKeyid(不是 hotspotKeyid)”
- get_location_accident_points
“查詢單一路口或路段某年度的事故位置,相同座標合併成「座標+件數」(件數多的在前);座標可能高度重複(同一路口可能落在同一點),不要當成逐案精確位置;只支援全年(不能指定月份);locationKeyid 與 kind 取自 get_cbi_hotspots 的結果”
3 inputs, 3 required
yearintegerrequired“民國年,106 起到今年,例如 114”kindstringrequired“熱點類型,取自 get_cbi_hotspots 的 kind”locationKeyidstringrequired“地點代碼,取自 get_cbi_hotspots 的 locationKeyid(不是 hotspotKeyid)”
- get_location_overview
“一次查詢單一路口或路段的概況:熱點的肇因與碰撞類型分布、地點歷年(106 年起)件數趨勢、某年度的事故位置;只給 year 與 get_cbi_hotspots 同一列的 rowRef(已包含 kind、熱點代碼與地點代碼,不會配錯);事故位置的限制同 get_location_accident_points”
2 inputs, 2 required
yearintegerrequired“民國年,106 起到今年,例如 114”rowRefstringrequired“列參照,取自 get_cbi_hotspots 同一列的 rowRef;已包含 kind、熱點代碼與地點代碼”
- get_location_trend
“查詢單一路口或路段的歷年(106 年起)件數趨勢,以及指定年度(最多 5 個,省略時為上游已發布的最近 3 年)的肇因與碰撞類型;逐年說明哪些年度因未進入熱點排名而沒有肇因資料(不代表沒有事故);歷年資料的最後一年是初估值,不能單憑件數升降判斷改善成效;kind 與 locationKeyid 取自 get_cbi_hotspots 的結果,city、area 與 metric 用來掃描各年排名”
6 inputs, 3 required
kindstringrequired“熱點類型,取自 get_cbi_hotspots 的 kind”locationKeyidstringrequired“地點代碼,取自 get_cbi_hotspots 的 locationKeyid(不是 hotspotKeyid)”citystringrequired“縣市名稱,例如 屏東縣”areastring“ALL 或「縣市|鄉鎮」,例如 屏東縣|恆春鎮;用來縮小掃描排名的範圍”metricstring“掃描各年熱點排名用的指標;路口只進其他指標排名的年度,換指標才找得到”yearsarray“要查肇因的民國年度,1–5 個、106 起到今年、不可重複;省略時查上游已發布的最近 3 個年度”
- list_areason 23 other servers
“列出可查詢的縣市與鄉鎮,供 get_cbi_hotspots 的 city、area 參數使用”
1 input
citystring“指定縣市時列出該縣市的鄉鎮;不填則列出所有縣市”
- list_schoolson 3 other servers
“列出指定縣市(可再限定鄉鎮)與類型的學校,供 get_school_hotspots 的 schoolKeyid 使用”
3 inputs, 2 required
citystringrequired“縣市名稱,例如 屏東縣”areastring“ALL 或「縣市|鄉鎮」,例如 屏東縣|屏東市;可用 list_areas 查詢”schoolTypestringrequired“學校類型”
- get_school_hotspots
“查詢學校周邊一定半徑內的事故熱點,依分類(地點、好發時段、年齡、車種、碰撞類型、肇因、歷年統計)分組;schoolKeyid 取自 list_schools 或 get_school_rank”
3 inputs, 3 required
yearintegerrequired“民國年,106 起到今年,例如 114”schoolKeyidstringrequired“學校代碼,取自 list_schools 或 get_school_rank 的 schoolKeyid”radiusnumberrequired“半徑(公尺):100、150、200、500、1000”
- get_school_rank
“查詢指定年度、縣市(可再限定鄉鎮)與類型中,上游列出的排名前列學校(順序看起來是排名,但排名指標上游未公開,也不是完整排名),結果可接 get_school_hotspots”
4 inputs, 3 required
yearintegerrequired“民國年,106 起到今年,例如 114”citystringrequired“縣市名稱,例如 屏東縣”areastring“ALL 或「縣市|鄉鎮」,例如 屏東縣|屏東市;可用 list_areas 查詢”schoolTypestringrequired“學校類型”
- get_school_accident_points
“查詢學校周邊一定半徑內某年度的事故位置,相同座標合併成「座標+件數」(件數多的在前);座標高度重複(與 AccPoints 相同的行為),不要當成逐案精確位置;schoolKeyid 取自 list_schools 或 get_school_rank”
3 inputs, 3 required
yearintegerrequired“民國年,106 起到今年,例如 114”schoolKeyidstringrequired“學校代碼,取自 list_schools 或 get_school_rank 的 schoolKeyid”radiusnumberrequired“半徑(公尺):100、150、200、500、1000”
Show 7 more tools
- get_period_comparison
“查詢縣市(或全國)某年某月累計的交通事故死傷人數,並與上游提供的比較期間(預設去年同期)比較;回傳事故總件數與指定指標(headline:事故總件數,加 30日死亡/事故受傷/事故死傷),以及依年齡、用路人、肇因等分類的 breakdown;metric 選「全部」時對死亡、受傷、死傷各查一次(3 個上游請求),輸出改依指標分組(byMetric)。酒駕、毒駕問題請用本工具。breakdown …”
6 inputs, 3 required
citystringrequired“縣市名稱(如 屏東縣),或 全國、國道、其他”yearintegerrequired“民國年,例如 115”monthstringrequired“累計到幾月,01–12(例如 07 表示 1–7 月累計)”metricstring“死亡人數是事故發生後 30 日內死亡;全部=死亡、受傷、死傷三組一次回”compareWithstring“比較的基準”categorystring“選填;只回傳名稱包含這個字串的分類,例如 吸食違禁物駕駛(毒駕)、酒駕;headline 會是空的;沒帶時回傳全部分類”
- get_location_npa_cases
“查詢屏東縣 17 個路口某年(107–114 年)半徑 30 公尺內的警政署事故案件彙總;這是推算,未經人工標註,不是道安總動員的件數;locationKeyid 取自 get_cbi_hotspots 的結果,不在涵蓋範圍、沒有中心或 30 公尺內沒有案件時會說明,不代表 0 件或沒有事故”
2 inputs, 2 required
locationKeyidstringrequired“地點代碼,取自 get_cbi_hotspots 的 locationKeyid(不是 hotspotKeyid)”yearintegerrequired“民國年,107 到 114,例如 114”
- get_township_drunk_ranking
“查詢某縣市某年各鄉鎮的酒駕事故件數與死傷,回該縣市完整的鄉鎮列表(依死傷、案件、鄉鎮名稱排序);city 不填為屏東縣;口徑是警政署的肇因研判,不是道安總動員的數字,不可互比或推算占全縣市比例,也沒有跨縣市排名;目前只有 114 年,內建離線資料,不連上游”
2 inputs, 1 required
yearintegerrequired“民國年,目前只有 114”citystring“縣市名稱,22 縣市之一(寫法可用 list_areas 查),不填為屏東縣”
- get_county_drunk_enforcement
“查詢某年各縣市(22 縣市加署所屬機關)的酒駕舉發件數(cases,酒精濃度超過規定標準者)與毒駕舉發件數(drugCases,吸食毒品迷幻藥麻醉品及其相類似之管制藥品者,資料集 39362);這些是行政舉發件數,不是事故件數,反映執法強度而非酒駕或毒駕發生率,不可與道安總動員或警政署統計查詢網的數字互比;毒駕舉發的 114 年數字與交通部草案說明差 616、與 113 年差 4.9 倍,原因不…”
1 input, 1 required
yearintegerrequired“民國年,目前只有 114”
- get_improvement_progress
“查詢首頁六個改善進度分頁(路口行人安全設施、人行道、減少路側障礙物、校園周邊、行人早開時相、行人專用時相)各縣市的預期改善數與實際完成數,照網站用語,不加單位也不計算完成率(網站沒有標示單位);統計年月由網站決定、各主題不同,輸出的 dataPeriod 附網站的「統計至」說明;校園周邊的說明與請求月份可能不一致,會在 notes 說明”
1 input, 1 required
subjectstringrequired“網站分頁名稱;校園周邊沒有「改善進度」字尾”
- get_crosswalk_setback_count
“查詢首頁「行人穿越道退縮完成數」分頁各縣市的目前數量(current,照網站圖例用語),不加單位、不算合計也不判斷縣市好壞(網站沒有標示單位與統計口徑);上游給 null 的縣市(如連江縣)輸出 null 並在 notes 說明,不代表 0;刻意不公開上游圖例稱「與上月比較」的欄位(最新月份小於實際月增量,口徑不明);統計年月由網站決定,輸出的 dataPeriod 是請求用的年月”
Takes no inputs.
- list_speed_enforcement_points
“列出某縣市(或「國道」)的測速執法設置點:地址、座標、拍攝方向與速限,可用 area 再指定鄉鎮;資料來自警政署「測速執法設置點」資料集,內建離線、不連上游;資料集沒有區分固定式與移動式,也不是事故資料,不能用來判斷哪裡較危險或測速是否有效;資料集沒有連江縣的列(回空清單並說明,不代表沒有測速);少數座標明顯錯誤的列標 coordinateSuspect: true(座標原樣輸出,請勿用來定位,…”
2 inputs, 1 required
citystringrequired“22 縣市之一(寫法可用 list_areas 查),或「國道」(國道公路警察局負責的設置點)”areastring“鄉鎮名稱,須與資料集的寫法相同(例如 屏東市;查不到時 notes 會列出有列的鄉鎮);city 為「國道」時不可帶”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-13.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 98% of 49
- Tools with a description
- 100% of 19
- Typical description length
- 169 characters
The tool set
Counted from the listing
- Tools
- 19
- Size of the list
- about 3,257 tokens for an agent to load (characters ÷ 4)
- Naming
- 18 of 19 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 19 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-13 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://roadsafety.taux.io/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"roadsafety-mcp": {
"url": "https://roadsafety.taux.io/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"roadsafety-mcp": {
"type": "http",
"url": "https://roadsafety.taux.io/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"roadsafety-mcp","type":"http","url":"https://roadsafety.taux.io/mcp"}'Claude Code
claude mcp add --transport http roadsafety-mcp https://roadsafety.taux.io/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"roadsafety-mcp": {
"type": "streamableHttp",
"url": "https://roadsafety.taux.io/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"roadsafety-mcp": {
"httpUrl": "https://roadsafety.taux.io/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.roadsafety-mcp] url = "https://roadsafety.taux.io/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"roadsafety-mcp": {
"url": "https://roadsafety.taux.io/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://roadsafety.taux.io/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-13. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-13. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-13. Source: read 2026-11-13.
- Cline marketplace. Not in the Cline marketplace on 2026-11-13. Source: read 2026-11-13.
Own host
- security.txt. No security.txt at https://roadsafety.taux.io/.well-known/ (HTTP 404, 2026-11-13). Source: roadsafety.taux.io/.well-known/security.txt · read 2026-11-13.
- A2A agent card. No A2A agent card at https://roadsafety.taux.io/.well-known/ (HTTP 404, 2026-11-13). Source: roadsafety.taux.io/.well-known/agent-card.json · read 2026-11-13.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint roadsafety.taux.io/mcp | Session opened | matches | our test · 2026-11-13 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-13 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-13. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about io.github.foxhsiao/roadsafety-mcp
Answered from the data aboveWho publishes io.github.foxhsiao/roadsafety-mcp?
The registry ties the namespace io.github.foxhsiao to the GitHub account foxhsiao; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does io.github.foxhsiao/roadsafety-mcp need an API key or sign-in?
It opened a session without any credential on 2026-11-13. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.foxhsiao/roadsafety-mcp been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (no operator permission)
We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-11-13, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 959 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 19 tools, 0 resources, 0 prompts.
- 2,110 msFinished: 2 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “io.github.foxhsiao/roadsafety-mcp: MCP server record.” Data checked 2026-11-13. https://protocolprobe.com/mcp/servers/io.github.foxhsiao/roadsafety-mcp
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/io.github.foxhsiao/roadsafety-mcp)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology