Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
AI auction radar is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
7
tools declared
remote
at its publisher
—
calls last 7d
What it does
Taiwan court auction case search via WeiDu: Search for cases, individual case details and risk keywords, county/city administrative district overview, knowledge base, price reduction tiers, and overdue difference calculation. Free and registration-free.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http ai-auction-radar-mcp https://foreclosure-radar.com/mcp
# 2 — ask your agent for something these tools do
# get_auction_overview, search_auctions, get_auction_case and 4 more
AI auction radar costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
FRAll 1 server
foreclosure-radar1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http ai-auction-radar-mcp https://foreclosure-radar.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
回傳 AI法拍雷達收錄的法拍案件概況：進行中與停拍件數、房屋／土地／動產件數、7 天與 30 天內開標件數、近期新上架，以及資料更新到什麼時候（司法院系統停機時會明講資料停更）。回答「現在有多少法拍」前先看這個。
No parameter schema on file.
依縣市、行政區、類型（房屋／土地／動產）、拍次、點交、開標日期範圍、法院、地址關鍵字、風險字樣排除、空屋、全部產權篩選進行中的法拍案件，最多 10 筆；每筆有地址、法院與案號、拍次、開標日、點交、公告風險字樣、使用分區與案件頁網址。不提供底價，也不能依價格篩選或排序（底價登入網站後查看）。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| county | string | no | 縣市，臺／台皆可。可用：基隆市、臺北市、新北市、桃園市、新竹市、新竹縣、苗栗縣、臺中市、彰化縣、南投縣、雲林縣、嘉義市、嘉義縣、臺南市、高雄市、屏東縣、宜蘭縣、花蓮縣、臺東縣、澎湖縣、金門縣、連江縣 |
| district | string | no | 鄉鎮市區，例如「大安區」；要同時給 county |
| kind | string | no | house＝房屋、land＝土地、movable＝動產 |
| round | string | no | 拍次：1～4＝第幾拍（4＝第 4 拍以上）、buy＝特別程序（應買） |
| handover | string | no | 公告「點交」欄：Y＝點交、N＝不點交（只看公告明確寫的） |
| sale_within_days | integer | no | 開標日在今天起幾天內（不含應買） |
| court | string | no | 法院名稱關鍵字，例如「臺北」「新北」 |
| keyword | string | no | 地址、地號或案號關鍵字 |
| exclude_risks | string | no | 不要有這些風險字樣，逗號分隔。可用：occ、rent、illegal、defect、death、noroad、landbuild、unclear、prior（沒解析到的案件不受影響） |
| vacant_only | boolean | no | 只看公告標示空屋或空地的 |
| whole_ownership_only | boolean | no | 只看全部產權（排除持分與公同共有） |
| status | string | no | 進行中（預設）、停拍、或全部 |
| sort | string | no | sale_date＝開標日由近到遠、newest＝最近上架。刻意沒有價格排序 |
| limit | integer | no | 最多回幾筆（上限 10） |
用案件 id 或案件頁路徑查一案的公開資訊：標的物（地址／地號、面積、權利範圍、點交）、拍次與開標日、公告風險字樣（附判定依據）、公告載明的使用分區、承買資格限制、拍次變化記錄。底價、拍定價與官方公告 PDF 需登入網站查看，會在 locked_on_website 說明。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case | string | yes | 案件 id（search_auctions 回的 id，例如 TPD_115_司執_085340），或案件頁路徑（例如 TPD/115-司執-085340） |
查某縣市或某行政區進行中的法拍件數、房屋／土地／動產分布、最近開標日、30 天內開標件數、公告點交比例；不給縣市時列出各區件數。不含底價或行情。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| county | string | yes | 縣市，臺／台皆可。可用：基隆市、臺北市、新北市、桃園市、新竹市、新竹縣、苗栗縣、臺中市、彰化縣、南投縣、雲林縣、嘉義市、嘉義縣、臺南市、高雄市、屏東縣、宜蘭縣、花蓮縣、臺東縣、澎湖縣、金門縣、連江縣 |
| district | string | no | 鄉鎮市區（可省略，省略則列出該縣市各區的件數） |
給第一拍的底價（你自己填的數字），算出二拍、三拍底價「依法不會低於」多少（強制執行法第 91、92 條：每次酌減不得逾 20%，所以二拍不低於 80%、三拍不低於 64%）；選填目前公告底價，可再算「下一次減價的最低可能」。這是法定下限不是預測，不查任何案件、不提供案件底價。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| first_round_price_twd | number | yes | 第一拍的底價（新臺幣元）。由你提供，這個工具不會去查任何案件 |
| current_price_twd | number | no | （選填）目前公告的底價（元）；給的話會多算「再減一次依法最低不會低於多少」 |
給得標價與已繳保證金（你自己填的數字），算尾款（得標價減保證金）；若逾期不繳，依強制執行法第 68-2 條試算「再拍賣價金低於原得標價加費用」的差額、保證金能不能抵、還欠多少。再拍賣價金與費用是你的假設（不給就回 100%／90%／80%／70% 對照），不是預測。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| bid_price_twd | number | yes | 得標價（新臺幣元） |
| deposit_twd | number | yes | 已繳保證金（元，不可大於得標價） |
| resale_price_twd | number | no | （選填）假設的再拍賣價金（元）；給的話算單一情境，不給就回 100%／90%／80%／70% 四種對照 |
| resale_cost_twd | number | no | （選填）假設的再拍賣所生費用（元，預設 0） |
用問題或關鍵字檢索 AI法拍雷達的法拍知識庫（強制執行法、土地法等法條逐條核對）：點交與不點交、優先承買權、繳款期限與逾期差額、農地與原住民保留地誰不能買、公告怎麼讀等，回傳摘要、簡短回答、法規出處（全國法規資料庫）與查證日。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | 問題或關鍵字，例如「不點交是什麼意思」「拍到後要多久繳款」「農地誰不能買」 |
| limit | integer | no | 最多回幾篇（上限 5） |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AI auction radar or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.1.0 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest7852e81d879395e7e6da8afae3a0778318a47c6621381fe39fe2185ef43fa194
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_auction_overview | no tags | |
| search_auctions | no tags | |
| get_auction_case | no tags | |
| get_district_overview | no tags | |
| calc_price_cut_floor | no tags | |
| calc_payment_shortfall | no tags | |
| search_guides | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest7852e81d879395e7
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.0.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish AI auction radar can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.