Cure Cancer With AI

io.github.hifarrer由 GitHub 账号 hifarrer 发布v1.0.0更新于 Oct 24, 2026

Free oncology data (research, trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions.

已验证Streamable HTTP可网页运行知识与记忆数据与分析AI 与机器学习

概览

AI 生成的概览

远程 MCP 服务器,提供肿瘤学数据(PubMed 论文、新闻、FDA 批准、临床试验)以及 IBM MAMMAL 生物医学预测。

可以做什么
  • 跨全部数据集一次性搜索研究论文、新闻、博客文章、FDA 批准与临床试验
  • 列出并获取肿瘤学研究论文、新闻、博客文章、FDA 批准药物与临床试验,可按癌症类型、关键词、状态或日期筛选
  • 按 id、slug 或 NCT 编号获取单篇论文、单篇博客或单个试验(含入组标准与地点)
  • 用 IBM MAMMAL 预测蛋白–蛋白相互作用、药物–靶点结合亲和力(pKd)与 ClinTox 试验毒性
  • 按示例药物或目标特征搜索药物化合物,并列出可用的特征
  • 检查 MAMMAL 预测模型是否已加载就绪
适用场景
适合需要查询肿瘤学文献、临床试验、FDA 药物批准或癌症新闻,或对蛋白对、药物–靶点对、化合物做快速生物医学模型预测的场景。适用于需要干净 JSON 且使用免费密钥的研究工具、仪表盘和智能体。
运行要求
远程 Streamable HTTP 端点,无需本地安装。需要从提供方网站获取免费 API 密钥,并以 Authorization Bearer 令牌请求头发送。免费额度为每个密钥每小时 100 次请求。需能访问提供方主机。
安装前请注意
API 密钥是放在 Authorization 请求头中的机密,勿写入共享配置或日志。MAMMAL 预测为 CPU 计算,可能耗时约 60 秒,存在超时风险。数据仅供参考,不构成医疗建议,展示结果时应引用来源链接。查询内容会发送至第三方服务。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Cure Cancer With AI,将其添加到工作区。
  2. 连接 Authorization token 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.hifarrer%2Fcure-cancer-with-ai/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "cure-cancer-with-ai": {
      "type": "http",
      "url": "https://www.curecancerwithai.com/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

Cure Cancer With AI — Public API

A free public REST API and MCP server for oncology data: peer-reviewed research papers (PubMed), curated cancer news, FDA-approved oncology drugs, clinical trials, and a cross-dataset keyword search — plus IBM MAMMAL biomedical foundation-model predictions (protein–protein interaction, drug–target affinity, and ClinTox clinical-trial toxicity).

Base URL: https://www.curecancerwithai.com · Docs: https://www.curecancerwithai.com/developers · OpenAPI 3.1 spec · Agent instructions

[OpenAPI] [MCP] [License: MIT]


What it's for

If you need to programmatically access oncology research, clinical trials, FDA approvals, or cancer news, or to run biomedical model predictions (protein–protein interaction, drug–target binding affinity, drug toxicity), this API gives you clean JSON with a free API key. It's a good fit for research tools, dashboards, chatbots, and AI agents.

Quickstart

  1. Get a free API key — sign in at https://www.curecancerwithai.com/api-keys and click Create key (format ccw_live_..., shown once).
  2. Send it on every request as a Bearer token:
bash
curl "https://www.curecancerwithai.com/api/v1/search?q=osimertinib&types=research,fdaApprovals" \  -H "Authorization: Bearer ccw_live_YOUR_KEY"
  • Auth: Authorization: Bearer ccw_live_... (or x-api-key: ccw_live_...)
  • Free tier: 100 requests/hour per key (rolling window). Watch X-RateLimit-Remaining; on HTTP 429 wait for Retry-After.
  • List endpoints return { data: [...], pagination: {...} }; single-record endpoints return { data: {...} }; errors return { error: "..." }.

Endpoints

MethodPathDescription
GET/api/v1/researchPeer-reviewed oncology research papers (PubMed)
GET/api/v1/research/{idOrPubmedId}A single research paper
GET/api/v1/newsCurated cancer news
GET/api/v1/blogEditorial blog posts (excerpts)
GET/api/v1/blog/{slug}A single blog post (full content)
GET/api/v1/fda-approvalsFDA-approved oncology drugs
GET/api/v1/clinical-trialsClinical trials from public registries
GET/api/v1/clinical-trials/{nctId}A single trial (eligibility + locations)
GET/api/v1/searchCross-dataset keyword search (all datasets at once)
POST/api/v1/mammal/ppiMAMMAL: protein–protein interaction
POST/api/v1/mammal/dtiMAMMAL: drug–target interaction (pKd)
POST/api/v1/mammal/clintoxMAMMAL: ClinTox clinical-trial toxicity

Common query params on list endpoints: limit (1–100, default 20), offset, and usually cancerType, search, from/to. Full details and field lists are in the OpenAPI spec and AGENTS.md.

MCP server (for AI agents)

There's a remote Model Context Protocol server over Streamable HTTP that exposes every endpoint above as a tool, so Claude, ChatGPT, and other MCP clients can call the API directly.

  • Endpoint: https://www.curecancerwithai.com/api/mcp
  • Auth: send Authorization: Bearer ccw_live_YOUR_KEY as a header.
json
{  "mcpServers": {    "cure-cancer-with-ai": {      "url": "https://www.curecancerwithai.com/api/mcp",      "headers": { "Authorization": "Bearer ccw_live_YOUR_KEY" }    }  }}

Tools: search_oncology, list_research, get_research_paper, list_news, list_blog_posts, get_blog_post, list_fda_approvals, list_clinical_trials, get_clinical_trial, predict_ppi, predict_dti, predict_clintox, mammal_health. See mcp/.

Examples

Runnable samples in examples/: curl.sh, javascript.mjs, python.py. Import openapi.json into Postman or any OpenAPI tool, or use the Postman collection.

Disclaimer

All data is for informational purposes only and is not medical advice. Cite source URLs (url, fullTextUrl, labelPdfUrl) when presenting results to users.

Links

来源:README.md,提交 31cffff

工具

15

search_oncology

Search all oncology datasets

Search a keyword across every Cure Cancer With AI dataset at once — research papers, news, blog posts, FDA approvals, and clinical trials — with results grouped by type. Use this first for broad discovery, then fetch a single record by id/slug/nctId for full detail.

输入参数q必填limittypescancerType

list_research

List research papers

List peer-reviewed oncology research papers ingested from PubMed (abstracts, authors, journal, plain-language summaries). Filter by cancer type, treatment type, keyword, or publication date.

输入参数tofromlimitoffsetsearchcancerTypetreatmentType

get_research_paper

Get a research paper

Fetch a single research paper by its internal id or PubMed id.

输入参数idOrPubmedId必填

list_news

List cancer news

List curated cancer news articles aggregated from trusted sources. Filter by cancer type, keyword, or published date.

输入参数tofromlimitoffsetsearchcancerType

list_blog_posts

List blog posts

List editorial blog articles (excerpts). Use get_blog_post for full content. Filter by category, cancer-type tag, or keyword.

输入参数limitoffsetsearchcategorycancerType

get_blog_post

Get a blog post

Fetch a single blog post by slug, including the full article content.

输入参数slug必填

list_fda_approvals

List FDA approvals

List FDA-approved oncology drugs with indication, company, approval date, and label links. Filter by cancer type, keyword, or approval date.

输入参数tofromlimitoffsetsearchcancerType

list_clinical_trials

List clinical trials

List clinical trials from public registries (conditions, status, intervention type). Filter by condition, status (e.g. RECRUITING), or keyword.

输入参数limitoffsetsearchstatuscondition

get_clinical_trial

Get a clinical trial

Fetch a single clinical trial by NCT id (or internal id), including eligibility criteria and locations.

输入参数nctId必填

predict_ppi

Predict protein–protein interaction

Predict the binding-affinity class for a pair of proteins using the IBM MAMMAL biomedical foundation model. Returns label "1" (interacting) or "0" (non-interacting). Inference is CPU-bound and may take up to ~60s.

输入参数protein_a必填protein_b必填

predict_dti

Predict drug–target interaction (pKd)

Predict drug–target binding affinity as pKd (−log10 Kd; higher = stronger binding) using IBM MAMMAL. Inference is CPU-bound and may take up to ~60s.

输入参数drug_seq必填norm_y_stdtarget_seq必填norm_y_mean

predict_clintox

Predict clinical-trial toxicity (ClinTox)

Predict clinical-trial toxicity for a compound using IBM MAMMAL. Returns pred 1 (toxic / likely to fail trials) or 0 (not toxic) plus a raw score. Inference is CPU-bound and may take up to ~60s.

输入参数smiles必填

search_compounds

Search pharmaceutical compounds

Find pharmaceutical compounds two ways: by example drugs you already know (fuzzy-matched), or by setting target characteristics on a −4…+4 scale. Provide exactly one of `examples` or `preferences`. Use list_compound_characteristics for the available preference names.

输入参数limitexamplespreferencesinclude_characteristics

list_compound_characteristics

List compound characteristics

List the pharmaceutical-compound characteristics (each scored on the −4…+4 scale) that can be used as preference keys in search_compounds.

无需输入参数。

mammal_health

Check MAMMAL model health

Check whether the IBM MAMMAL prediction model is loaded and ready. No API key required. Call this before predict_* tools if a prior prediction timed out.

无需输入参数。

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。