Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
Nothing to run from here
MedicineData 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
22
tools declared
remote
at its publisher
—
calls last 7d
What it does
Chinese pharma data MCP: 22 tools covering drugs, trials, deals, patents, sales. Per-row billing.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http medicinedata-mcp https://medicine.shanchuangkj.com/mcp/ --header 'X-API-Key: ${X_API_KEY}'
# 2 — ask your agent for something these tools do
# list_capabilities, search_drugs, get_drug_detail and 19 more
It needs X_API_KEY (API key from https://medicine.shanchuangkj.com/mcp (2,000 free rows on signup)): this sends it in the X-API-Key header from your environment, so export it first — its endpoint answers 401 without it.
MedicineData costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SHAll 1 server
shanchuangkj1 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 Code reads X_API_KEY (API key from https://medicine.shanchuangkj.com/mcp (2,000 free rows on signup)) from your environment each time it connects and sends it in the X-API-Key header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx X_API_KEY … and open a new terminal (Windows).
claude mcp add --scope user --transport http medicinedata-mcp https://medicine.shanchuangkj.com/mcp/ --header 'X-API-Key: ${X_API_KEY}'Reconnect, 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 — but its publisher asks for a key of their own on every call.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: X-API-Key header — API key from https://medicine.shanchuangkj.com/mcp (2,000 free rows on signup).. You set it in your own client’s config, on your machine — this marketplace never holds it.
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
22 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.
列出本 MCP 的全部工具、能力域、限额与套餐。不计费，接入后第一件事就是调它。
No parameter schema on file.
按药名/英文名/别名、药物类型、全球或国内研发阶段、企业检索药品（rs_medical，7.6 万行）。阶段枚举：临床前/临床I期/临床I/II期/临床II期/临床II/III期/临床III期/批准临床/申请临床/申请上市/批准上市/暂无进度/(非积极)/(已撤市)。返回摘要列，完整记录走 get_drug_detail。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | 药名或英文名，模糊匹配 |
| category | string | no | 化药 / 生物药 / 中药/天然产物 / 其他 |
| stage_global | string | no | 全球阶段，精确匹配枚举值 |
| stage_china | string | no | 国内阶段，精确匹配枚举值 |
| company | string | no | 企业名，模糊 |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按 drug_id 取单条药品完整记录（适应症编码串、靶点、批准日期、研发企业、链接等）。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| drug_id | string/integer | yes | search_drugs 返回的 id |
按靶点找在研/上市药品（命中 rs_medical.target，形如 ADRB(批准上市);GR(批准上市)）。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | yes | 靶点名，如 PD-1 / KRAS G12C |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按适应症找药品（命中 rs_medical.indication，编码串 阶段|适应症名|适应症id）。返回额外给 indication_matched：已按关键词筛好的 阶段/适应症名/id。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| indication | string | yes | 适应症名，如 肺癌 / 特发性肺纤维化 |
| stage | string | no | 可选，限定研发阶段（如 临床III期 / 批准上市） |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
检索靶点树（rs_target，9.5k 行）：靶点名、别名、父节点。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | yes | 靶点名或别名 |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按 target_id 取靶点：上级链 ancestors + 子靶点 children + 关联药品数 drug_count。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target_id | string/integer | yes | search_targets 返回的 id |
检索适应症树（rs_indication，8.7k 行）：中英文名、别名、父节点/根节点。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | yes | 适应症中/英文名 |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按 indication_id 取适应症：上级链 + 子节点 + 药品数 + 试验数。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| indication_id | string/integer | yes | search_indications 返回的 id |
检索临床试验。source=cn 中文库（2.6 万条，phase 取 std_phase 中文枚举，可按 keyword/phase/company 筛；该库 status 列实测恒为 1、无状态语义，返回 null）；source=global 全球库 ClinicalTrials.gov（48 万条，status 为英文枚举 RECRUITING / COMPLETED / TERMINATED 等原值，另有少量中文值如「已完成」可用模糊词命中）。两个来源返回同一套字段名：trial_no/title/drug/target/indication/phase/status/sponsor。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | 试验标题/药物/靶点/适应症 |
| phase | string | no | 分期，如 III期 / Phase 3 |
| status | string | no | 状态，仅 source=global；给英文枚举原值按精确匹配，给中文词按模糊匹配 |
| company | string | no | 申办方/企业 |
| source | string | no | cn 或 global，默认 cn |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按 trial_id + source 取试验详情。中文库给入组人数/评价指标/AI 摘要；全球库给入排标准与结局指标（长文按 4000 字截断）。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| trial_id | string/integer | yes | search_clinical_trials 返回的 id |
| source | string | no | cn 或 global，默认 cn |
检索公司与机构（rs_company，5.1 万行）：中英文名、注册地、上市类型、母公司。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | 公司名 |
| country | string | no | 注册地，前缀匹配（库内形如 中国内地-上海 / 上海市 > 浦东新区） |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按 company_id 取公司详情 + 关联计数：管线药品数、BD 交易数、投融资事件数。某个计数超时会在 count_errors 里点名，不会静默当 0。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| company_id | string/integer | yes | search_companies 返回的 id |
检索 BD 交易（fa_drug_trade，4k 条）：license-in/out、首付款、总金额、里程碑、双方企业。trade_type 是分号组合串（授权/许可、投资;期权;合作、并购）。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | 交易标的名或双方企业名 |
| target | string | no | 靶点 |
| trade_type | string | no | 交易类型关键词 |
| year_from | string/integer | no | 起始年 YYYY |
| year_to | string/integer | no | 截止年 YYYY |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按 deal_id 取交易完整记录（金额结构、许可类型、双方企业 id）。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deal_id | string/integer | yes | search_deals 返回的 id |
检索投融资事件（fa_investment，1.8 万条）：轮次、金额、领投方、跟投方、时间。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| company | string | no | 被投企业名 |
| round | string | no | 轮次，如 A轮 / B轮 / 战略融资 |
| country | string | no | 地区，前缀匹配 |
| investor | string | no | 投资机构名（在 investors 串里模糊） |
| date_from | string | no | 起始日 YYYY / YYYY-MM / YYYY-MM-DD |
| date_to | string | no | 截止日 同上 |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
检索投资机构（fa_investor，2.5 万家）：类型、总部、关注阶段、关注赛道。参投次数这里不给（要按机构名全表计数，成本不可控），改用 search_investments 的 investor 参数按事件查。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | 机构名 |
| focus_stage | string | no | 关注阶段，如 早期 / A轮 |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
检索药品专利（rs_drug_patents，2.7 万条）：申请号、标题、法律状态、届满日、申请人。year_from / year_to 按届满年份比较。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| drug | string | no | 药品名 |
| ingredient | string | no | 成分名 |
| company | string | no | 企业或申请人 |
| status | string | no | 法律状态关键词 |
| year_from | string/integer | no | 届满年起始 |
| year_to | string/integer | no | 届满年截止 |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按 patent_id 取专利详情 + 关联药品/成分（linked_drugs，最多 20 条）。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| patent_id | string/integer | yes | search_patents 返回的 id |
检索医学会议摘要（rs_meeting_report，45 万条，ASCO / ESMO / SABCS 等）。⚠️ 本域只有会议摘要，没有 PubMed 题录（库里 rs_pubmed 实测 0 行）；created_year 是入库年份，不是发表年份。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | 摘要标题关键词 |
| domain_id | string/integer | no | 领域节点 id（见 search_indications） |
| year_from | string/integer | no | 入库年起始 |
| year_to | string/integer | no | 入库年截止 |
| fields | array/string | no | 列裁剪，取值见返回列名；默认给摘要列 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
按 report_id 取会议摘要详情（meta 含作者与正文摘要，长文按 4000 字截断）+ 原文链接。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| report_id | string/integer | yes | search_meeting_reports 返回的 id |
检索药品销量（2016–2024）。channel：drug=药品汇总（46 万行）、hospital=医院端（133 万行）、network=线上电商（京东/天猫/抖音，36 万行）、all=三张表合并。⚠️ 必须带 drug 或 company；库内没有线下连锁药店动销。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| drug | string | no | 药品名 |
| company | string | no | 企业名 |
| channel | string | no | all / drug / hospital / network，默认 all |
| year | string/integer | no | 单一年份 |
| year_from | string/integer | no | 起始年 |
| year_to | string/integer | no | 截止年 |
| province | string | no | 省份/地区关键词 |
| limit | integer | no | 返回条数，默认 20，硬上限 20（超出自动压低） |
| offset | integer | no | 翻页偏移，默认 0；offset+limit 不得超过 1000 |
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 MedicineData 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 1.0.2 · 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 digest109c0c44eeda9c99fa03f37fe570db432f6df619445efe9fcf126977638f60b3
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 |
|---|---|---|
| list_capabilities | no tags | |
| search_drugs | no tags | |
| get_drug_detail | no tags | |
| search_drugs_by_target | no tags | |
| search_drugs_by_indication | no tags | |
| search_targets | no tags | |
| get_target_detail | no tags | |
| search_indications | no tags | |
| get_indication_detail | no tags | |
| search_clinical_trials | no tags | |
| get_clinical_trial_detail | no tags | |
| search_companies | no tags | |
| get_company_detail | no tags | |
| search_deals | no tags | |
| get_deal_detail | no tags | |
| search_investments | no tags | |
| search_investors | no tags | |
| search_patents | no tags | |
| get_patent_detail | no tags | |
| search_meeting_reports | no tags | |
| get_meeting_report_detail | no tags | |
| search_market_sales | 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 digest109c0c44eeda9c99
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 1.0.2.
1.0.2
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 MedicineData 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.