Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Okay, MCP checkup done 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.
What it does
Group health checkup tiered plans, store search, health checkup FAQs, and corporate consultations, covering 241 cities.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http okay-mcp-checkup-done https://ai.ihaola.com.cn/api/mcp/haola-pe
# 2 — ask your agent for something these tools do
# vendor_list, vendor_brands, order_list and 22 more
Okay, MCP checkup done costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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.
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 okay-mcp-checkup-done https://ai.ihaola.com.cn/api/mcp/haola-peReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
25 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.
[匿名可调用] 查门店地址。支持三种方式,至少传一种:1) hospitalCode(可带 vendorids,按第一个品牌查);2) longitude+latitude(可带 radius 米,默认 50000,可带 vendorids);3) province/city/district(可带 vendorids)。外部调用仅支持 health100/haolaruici,partnerid 仅内部可用。不确定品牌和覆盖城市时先用 vendor.brands。本体: vendor → Action: list
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | — |
| province | string | no | — |
| district | string | no | — |
| hospitalCode | string | no | — |
| longitude | number | no | — |
| latitude | number | no | — |
| radius | number | no | — |
| vendorids | array | no | — |
[匿名可调用] 查各体检品牌覆盖的城市(品牌聚合摘要,不返回具体门店)。本体: vendor → Action: brands
Takes no parameters.
[需要登录] 查订单。查询 userOrders 集合。调用方归属甲方由服务端身份解析,filter 中无需传 partnerid。支持 $gte/$lte 日期范围、$in/$or 多值匹配。本体: order → Action: list 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | — |
| page | number | no | — |
| filter | object | no | — |
[需要登录] 查用户体检件。查询 userWelfare 集合。传 {customerMobile: "138xxx"} 或 {name: "张三"} 查对应用户的体检件。已知 userid 可直接传 {userid: "xxx"}。本体: welfare → Action: list 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ID | string | no | — |
| partnerid | string | no | — |
| userid | string | no | — |
| serviceid | string | no | — |
| rootid | string | no | — |
| mobile | string | no | — |
| name | string | no | — |
[匿名可调用] 提交企业商务咨询。企业客户有任何问题(合作咨询、产品了解、报价请求、投诉建议)均可提交,销售 24h 内联系。本体: corp → Action: inquiry
| Parameter | Type | Required | Notes |
|---|---|---|---|
| company | string | yes | — |
| contact | string | yes | — |
| phone | string | yes | — |
| employees | number | no | — |
| city | string | no | — |
| budget | string | no | — |
| message | string | no | — |
[匿名可调用] 查询好啦商务对接人(团检/商务合作):返回对接人姓名、电话、邮箱、二维码图片 URL。用户报价后需要人工商务对接时调用。本体: corp → Action: contact
Takes no parameters.
[匿名可调用] 企业团检报价:quotes 为对象数组,每档一个方案。每项 = { tier(档名,仅标识该档、不参与报价,返回时回填), budget(人均预算元,必填), healthConcerns(该档健康诉求,必填), populations?(人群数组 man/lady/girl,默认三人,该档) }。可选 partnerId(甲方 UUID),透传给 /plan/quotation 按伙伴定价。返回 data.list(每档 { tier, budget, planList, combinedPrice, discount }),其中 planList 为按人群的数组(每项 { population, price, items, planId }),逐档按人群拆分并发取值;planId 是该档该人群的方案标识,体检预约时传给 reservation.book,不要自己
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quotes | array | yes | — |
| partnerId | string | no | — |
[需要登录] 个人体检推荐:按调用方身份读用户名下体检件与模板,结合性别、婚姻状况、预算、健康诉求推荐体检项目,返回 data.selected_items(每项带 constraintId)与 planId。planId 直接传给 reservation.book 预约,不要自己拼项目。长耗时,建议每阶段调用 progress.report。本体: plan → Action: recommend 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| gender | string | yes | — |
| marital | string | no | — |
| age | number | no | — |
| budget | number | no | — |
| mainComplaint | string | no | — |
| reportHistory | string | no | — |
| userContext | string | no | — |
| welfareid | string | no | — |
| modification | string | no | — |
| previousPackage | array | no | — |
[匿名可调用] 体检 FAQ。不传 query 则列出所有问题。query 必须是短关键词(2-4字,如"报告"、"预约"、"空腹"),不要传完整问句。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
[匿名可调用] 按需查询领域知识。外部可用 URI: enums(状态码) / objects/contact(联系人) / objects/contact-profile(健康画像) / objects/checkup-proposal(企业团检方案顾问引导词)。查 action 参数用 help()。团检报价场景先用 knowledge_get({uri:"objects/checkup-proposal"}) 加载《企业团检方案顾问》引导词作为外部 MCP agent 的 system prompt,再调 plan_quotation;报价话术与输出模板必须遵循该引导词
| Parameter | Type | Required | Notes |
|---|---|---|---|
| uri | string | no | — |
[匿名可调用] 三级帮助系统。无参列出本体;传 ontology 列出该本体下工具;传 ontology 和 sub_action 查看参数,sub_action 用完整名称,如 vendor.list、plan.quotation。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ontology | string | no | — |
| sub_action | string | no | — |
[需要登录] 查询指定福利的详细内容,包括检查项目列表、规则说明、适用机构等。本体: welfare → Action: detail 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| welfareid | string | yes | — |
| vendorid | string | no | — |
[需要登录] 根据体检项目查询注意事项(饮食、用药、禁忌等)。需调用方用户标识(external_user_id 自动注入),partnerid 由服务端按用户标识解析,禁止客户端传。传 checkPackage 查套餐注意事项(必带 vendorid);传 serviceid 仅允许查本人订单。本体: knowledge → Action: cautions 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| checkPackage | object | no | — |
| vendorid | string | no | — |
| serviceid | string | no | — |
[需要登录] 查询单个订单完整详情,包括预约信息、医院信息、套餐项目、支付状态。本体: order → Action: detail 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceid | string | yes | — |
[需要登录] 按 relation/gender 查询当前用户的联系人。用户提到家人时必须先调用;唯一候选可直接使用 contactid,多个候选请用户选择,未选定时禁止保存画像。本体: contact → Action: list 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| relation | string | no | — |
| gender | string | no | — |
[需要登录] 查询指定就诊人的完整信息(含脱敏证件号)。本体: contact → Action: get 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| contactid | string | no | — |
| contactId | string | no | — |
[需要登录] 创建家属临时联系人。relation 必填,self 由系统创建;姓名、手机号、证件号可后补。本体: contact → Action: create 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| customerName | string | no | — |
| customerMobile | string | no | — |
| customerID | string | no | — |
| IDType | string | no | — |
| gender | string | no | — |
| birthday | string | no | — |
| marital | string | no | — |
| relation | string | yes | — |
[需要登录] 更新就诊人信息(姓名、手机号等)。本体: contact → Action: update 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| contactid | string | no | — |
| contactId | string | no | — |
| customerName | string | no | — |
| customerMobile | string | no | — |
| customerID | string | no | — |
| IDType | string | no | — |
| gender | string | no | — |
| birthday | string | no | — |
| marital | string | no | — |
[需要登录] 按 contactid 查询联系人的结构化健康画像。不传 contactid 时读取当前用户本人。本体: contact → Action: profile.get 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| contactid | string | no | — |
| contactId | string | no | — |
[需要登录] 仅在用户明确要求保存或更新长期健康画像时调用;仅推荐方案不得调用。本人不传 contactid,家人必须先解析唯一 contactid,禁止把家人信息写入本人档案。返回更新后的完整画像与 created。本体: contact → Action: profile.save 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| contactid | string | no | — |
| contactId | string | no | — |
| demographics | object | no | — |
| measurements | array | no | — |
| lifestyle | object | no | — |
| problem_list | array | no | — |
| family_history | array | no | — |
| allergy_intolerance | object | no | — |
| surgeries | array | no | — |
| medications | array | no | — |
| examinations | array | no | — |
| preferences_constraints | object | no | — |
[需要登录] 体检预约:按 planId 取出项目,交给伙伴接口下单。传 contactId 时直接使用该就诊人。没有 contactId 时,支持 elicitation form 的客户端会先选择已有联系人,或选择新建后填写姓名、手机号、证件类型、证件号、授权、出生日期和性别;出生日期和性别仅在非身份证时必填,服务端在提交后校验。不支持的客户端会收到 contactEntryUrl,用户可在 H5 添加就诊人后重新发起预约。不要在对话中要求用户发送身份证号。IDType 为 SFZ 时按身份证规则校验。体检项目只来自 planId,客户端不能提交项目。返回 serviceid 作为预约订单号、orderEntryUrl 作为订单列表页链接:用户在 H5 用手机号登录后可看到自己的订单,并可支付、改期/取消、查看检前注意事项、查看体检报告。渠道需要用户支付时返回支付链接 payUrl 和
| Parameter | Type | Required | Notes |
|---|---|---|---|
| planId | string | yes | — |
| hospitalCode | string | yes | — |
| vendorid | string | yes | — |
| appointmentDate | string | yes | — |
| timespan | string | no | — |
| contactId | string | no | — |
| contactid | string | no | — |
| IDType | string | no | — |
| payType | string | no | — |
[需要登录] 取消预约:按预约号取消;已支付订单会同时发起退款。预约号取自 reservation.book 返回的 serviceid。本体: reservation → Action: cancel 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reservationId | string | yes | — |
[需要登录] 更改预约日期:按预约号改期。本体: reservation → Action: modify 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reservationId | string | yes | — |
| appointmentDate | string | yes | — |
[需要登录] 根据卡号查卡密及兑换使用情况。welfareId 为空=未兑换,非空时串联福利和订单。本体: card → Action: list 鉴权:需要用户登录令牌,或已经绑定用户的云市场实例凭证。未登录调用返回 401;云市场实例未绑定用户时返回 code=40003 和 data.bindUrl。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cardId | string | yes | — |
| limit | number | no | — |
[匿名可调用] 长耗时任务进度上报。agent 每完成一个阶段调用一次,text 为给用户看的可读进度,如「报告解析中,预计 10 秒」。不落地业务数据,仅用于向用户展示过程。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| stage | string | no | — |
| percent | number | no | — |
- 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 Okay, MCP checkup done or to call it, at any volume.
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.
| 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 |
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.
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 |
|---|---|---|
| vendor_list | no tags | |
| vendor_brands | no tags | |
| order_list | no tags | |
| welfare_list | no tags | |
| corp_inquiry | no tags | |
| corp_contact | no tags | |
| plan_quotation | no tags | |
| plan_recommend | no tags | |
| faq | no tags | |
| knowledge_get | no tags | |
| help | no tags | |
| welfare_detail | no tags | |
| cautions | no tags | |
| order_detail | no tags | |
| contact_list | no tags | |
| contact_get | no tags | |
| contact_create | no tags | |
| contact_update | no tags | |
| contact_profile_get | no tags | |
| contact_profile_save | no tags | |
| reservation_book | no tags | |
| reservation_cancel | no tags | |
| reservation_modify | no tags | |
| card_list | no tags | |
| progress_report | 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
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 1.0.0.
No release note was published with this version.
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.
Any signed-in account that does not publish Okay, MCP checkup done can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.