Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

MedicineData MCP

REMOTE · MEDICINE.SHANCHUANGKJ.COM

Chinese pharma data MCP: 22 tools covering drugs, trials, deals, patents, sales. Per-row billing.

75 Trust /100

Last scanned (1 hour ago)

Scores higher than 68% of remote servers

Reachable. Last reached 24 Oct 2026.

Category Health and Science

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3233 tokens (~146/item across 22 items; 22 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
  • Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 23 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 24 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Oct 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Stability: unverified → 0.03 ▲ functional
    • “search_clinical_trials” reworded the description of “limit” cosmetic
    • “search_clinical_trials” reworded the description of “offset” cosmetic
    • “search_companies” reworded the description of “limit” cosmetic
    • “search_companies” reworded the description of “offset” cosmetic
    • “search_deals” reworded the description of “limit” cosmetic
    • “search_deals” reworded the description of “offset” cosmetic
    • “search_drugs” reworded the description of “limit” cosmetic
    • “search_drugs” reworded the description of “offset” cosmetic
    • “search_drugs_by_indication” reworded the description of “limit” cosmetic
    • “search_drugs_by_indication” reworded the description of “offset” cosmetic
    • “search_drugs_by_target” reworded the description of “limit” cosmetic
    • “search_drugs_by_target” reworded the description of “offset” cosmetic
    • “search_indications” reworded the description of “limit” cosmetic
    • “search_indications” reworded the description of “offset” cosmetic
    • “search_investments” reworded the description of “limit” cosmetic
    • “search_investments” reworded the description of “offset” cosmetic
    • “search_investors” reworded the description of “limit” cosmetic
    • “search_investors” reworded the description of “offset” cosmetic
    • “search_market_sales” reworded the description of “limit” cosmetic
    • “search_market_sales” reworded the description of “offset” cosmetic
    • “search_meeting_reports” reworded the description of “limit” cosmetic
    • “search_meeting_reports” reworded the description of “offset” cosmetic
    • “search_patents” reworded the description of “limit” cosmetic
    • “search_patents” reworded the description of “offset” cosmetic
    • “search_targets” reworded the description of “limit” cosmetic
    • “search_targets” reworded the description of “offset” cosmetic
  • 20 Oct 26 73

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Oct 2026 · Probed https://medicine.shanchuangkj.com/mcp/

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=medicine.shanchuangkj.com CN=YE2,O=Let's Encrypt,C=US 6 Sept 2026 5 Dec 2026 ECDSA 256 ECDSA-SHA384 56614e3a76a90598db1c64eac20e838be89
SANs: medicine.shanchuangkj.com
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of medicine.shanchuangkj.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
shanchuangkj.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On tool calls
HTTP status 200
Header Value
x-content-type-options nosniff

Protected resource metadata

Retrieved No
Problem no_resource_metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://medicine.shanchuangkj.com/mcp/ Verified 200
http (plaintext) http://medicine.shanchuangkj.com/mcp/ HTTPS enforced 301 https://medicine.shanchuangkj.com/mcp/
MCP tools · 22 exposed · ~3,113 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_clinical_trial_detail ~91

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)。

NameTypeReqDescription
sourcestring–cn 或 global,默认 cn
trial_idstring|integeryessearch_clinical_trials 返回的 id

No output schema declared.

No examples provided.

get_company_detail ~77

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。

NameTypeReqDescription
company_idstring|integeryessearch_companies 返回的 id

No output schema declared.

No examples provided.

get_deal_detail ~46

按 deal_id 取交易完整记录(金额结构、许可类型、双方企业 id)。

NameTypeReqDescription
deal_idstring|integeryessearch_deals 返回的 id

No output schema declared.

No examples provided.

get_drug_detail ~58

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)。

NameTypeReqDescription
drug_idstring|integeryessearch_drugs 返回的 id

No output schema declared.

No examples provided.

get_indication_detail ~53

按 indication_id 取适应症:上级链 + 子节点 + 药品数 + 试验数。

NameTypeReqDescription
indication_idstring|integeryessearch_indications 返回的 id

No output schema declared.

No examples provided.

get_meeting_report_detail ~61

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。

NameTypeReqDescription
report_idstring|integeryessearch_meeting_reports 返回的 id

No output schema declared.

No examples provided.

get_patent_detail ~53

按 patent_id 取专利详情 + 关联药品/成分(linked_drugs,最多 20 条)。

NameTypeReqDescription
patent_idstring|integeryessearch_patents 返回的 id

No output schema declared.

No examples provided.

get_target_detail ~53

按 target_id 取靶点:上级链 ancestors + 子靶点 children + 关联药品数 drug_count。

NameTypeReqDescription
target_idstring|integeryessearch_targets 返回的 id

No output schema declared.

No examples provided.

list_capabilities ~39

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。

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

search_clinical_trials ~296

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。

NameTypeReqDescription
companystring–申办方/企业
keywordstring–试验标题/药物/靶点/适应症
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
phasestring–分期,如 III期 / Phase 3
sourcestring–cn 或 global,默认 cn
statusstring–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

No output schema declared.

No examples provided.

search_companies ~156

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。

NameTypeReqDescription
countrystring–注册地,前缀匹配(库内形如 中国内地-上海 / 上海市 > 浦东新区)
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
keywordstring–公司名
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000

No output schema declared.

No examples provided.

search_deals ~207

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)。

NameTypeReqDescription
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
keywordstring–交易标的名或双方企业名
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
targetstring–靶点
trade_typestring–交易类型关键词
year_fromstring|integer–起始年 YYYY
year_tostring|integer–截止年 YYYY

No output schema declared.

No examples provided.

search_drugs ~288

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。

NameTypeReqDescription
categorystring–化药 / 生物药 / 中药/天然产物 / 其他
companystring–企业名,模糊
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
keywordstring–药名或英文名,模糊匹配
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
stage_chinastring–国内阶段,精确匹配枚举值
stage_globalstring–全球阶段,精确匹配枚举值

No output schema declared.

No examples provided.

search_drugs_by_indication ~193

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。

NameTypeReqDescription
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
indicationstringyes适应症名,如 肺癌 / 特发性肺纤维化
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
stagestring–可选,限定研发阶段(如 临床III期 / 批准上市)

No output schema declared.

No examples provided.

search_drugs_by_target ~142

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))。

NameTypeReqDescription
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
targetstringyes靶点名,如 PD-1 / KRAS G12C

No output schema declared.

No examples provided.

search_indications ~131

检索适应症树(rs_indication,8.7k 行):中英文名、别名、父节点/根节点。

NameTypeReqDescription
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
keywordstringyes适应症中/英文名
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000

No output schema declared.

No examples provided.

search_investments ~218

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。

NameTypeReqDescription
companystring–被投企业名
countrystring–地区,前缀匹配
date_fromstring–起始日 YYYY / YYYY-MM / YYYY-MM-DD
date_tostring–截止日 同上
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
investorstring–投资机构名(在 investors 串里模糊)
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
roundstring–轮次,如 A轮 / B轮 / 战略融资

No output schema declared.

No examples provided.

search_investors ~174

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。

NameTypeReqDescription
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
focus_stagestring–关注阶段,如 早期 / A轮
keywordstring–机构名
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000

No output schema declared.

No examples provided.

search_market_sales ~235

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。

NameTypeReqDescription
channelstring–all / drug / hospital / network,默认 all
companystring–企业名
drugstring–药品名
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
provincestring–省份/地区关键词
yearstring|integer–单一年份
year_fromstring|integer–起始年
year_tostring|integer–截止年

No output schema declared.

No examples provided.

search_meeting_reports ~210

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。

NameTypeReqDescription
domain_idstring|integer–领域节点 id(见 search_indications)
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
keywordstring–摘要标题关键词
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
year_fromstring|integer–入库年起始
year_tostring|integer–入库年截止

No output schema declared.

No examples provided.

search_patents ~206

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。

NameTypeReqDescription
companystring–企业或申请人
drugstring–药品名
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
ingredientstring–成分名
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000
statusstring–法律状态关键词
year_fromstring|integer–届满年起始
year_tostring|integer–届满年截止

No output schema declared.

No examples provided.

search_targets ~126

检索靶点树(rs_target,9.5k 行):靶点名、别名、父节点。

NameTypeReqDescription
fieldsarray|string–列裁剪,取值见返回列名;默认给摘要列
keywordstringyes靶点名或别名
limitinteger–返回条数,默认 20,硬上限 20(超出自动压低)
offsetinteger–翻页偏移,默认 0;offset+limit 不得超过 1000

No output schema declared.

No examples provided.

Install

How do I install the MedicineData MCP server?

MedicineData MCP is a hosted endpoint at https://medicine.shanchuangkj.com/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · medicine.shanchuangkj.com

# add to Claude Code
claude mcp add --transport http com-shanchuangkj-medicine-data 'https://medicine.shanchuangkj.com/mcp/'
Common questions

What is the MedicineData MCP server?

MedicineData MCP is listed in the public MCP registry as com.shanchuangkj/medicine-data. Chinese pharma data MCP: 22 tools covering drugs, trials, deals, patents, sales. Per-row billing. This page covers its hosted endpoint (https://medicine.shanchuangkj.com/mcp/).

Is the MedicineData MCP server safe to use?

MedicineData MCP scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the MedicineData MCP server expose?

MedicineData MCP exposes 22 tools: list_capabilities, search_drugs, get_drug_detail, search_drugs_by_target, search_drugs_by_indication, and 17 more. Their descriptions and schemas cost roughly 3,113 tokens of context every time the server is loaded.

Does the MedicineData MCP server require authentication?

Yes. MedicineData MCP asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the MedicineData MCP server still maintained?

MedicineData MCP is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.