Mediora MCP Server
Exposes a doctor-reviewed medical catalog of blood-test markers, clinical conditions, and patient symptoms as MCP tools in English, Russian, and Hebrew, supporting both anonymous queries and authenticated patient data analysis.
README
Mediora.AI — MCP Server
A hosted Model Context Protocol server that exposes Mediora.AI's doctor-reviewed medical catalog to AI agents — blood-test markers, clinical conditions and patient symptoms — as callable tools, in English, Russian and Hebrew.
- Endpoint:
https://mcp.mediora.ai/mcp(JSON-RPC 2.0 over streamable HTTP) - Discovery manifest:
https://mcp.mediora.ai/.well-known/mcp.json - Human landing:
https://mcp.mediora.ai/mcp/info - Website: https://www.mediora.ai
This repository is the public listing for a hosted server. It contains the registry manifest and connection instructions — not the server's source. Clients connect to the endpoint above; there is nothing to run locally.
Connect
Add to your MCP client. For Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"mediora": {
"type": "http",
"url": "https://mcp.mediora.ai/mcp"
}
}
}
No API key is required for the catalog tools. Restart the client and ask, e.g., "What does a high ferritin mean?" — the answer comes straight from Mediora's doctor-reviewed catalog.
Tools
Anonymous — catalog reads (no token)
| Tool | Returns |
|---|---|
mediora__list_markers |
Every blood-test marker (slug + short name) |
mediora__explain_marker |
Full doctor-reviewed explainer for one marker |
mediora__lookup_marker |
Fuzzy alias search across EN/RU/HE |
mediora__list_conditions |
Every clinical condition (slug + ICD-10) |
mediora__explain_condition |
Full explainer for a clinical condition |
mediora__list_symptoms |
Every patient-side symptom |
mediora__explain_symptom |
Symptom triage explainer with lab work-up |
Patient tools — require a Bearer JWT
| Tool | Returns |
|---|---|
mediora__whoami |
The authenticated patient's profile summary |
mediora__analyze_lab_pdf |
Upload a lab PDF/image for analysis (SSRF-guarded fetch) |
mediora__get_patient_history |
The patient's uploaded tests |
mediora__get_test_details |
A single test's markers + AI interpretation |
mediora__longitudinal_trend |
A marker's trend across the patient's uploads |
What it is — and isn't
- Interpretation, not a diagnosis. Mediora explains lab results; it never produces a diagnosis or replaces a clinician.
- No PHI in the read surface. The anonymous catalog tools carry no patient data. Patient tools require the patient's own JWT and return only that patient's data.
- Doctor-reviewed. Every catalog entry passes a 2-of-3 licensed-physician review before it goes live.
Languages
English · Russian · Hebrew — native interpretation, not machine translation. Pass a
lang argument (en | ru | he) to any catalog tool.
License
This repository (manifest + docs) is released under the MIT License. The catalog content served by the tools is licensed CC-BY-NC 4.0 — free to use with attribution to Mediora.AI (link to https://www.mediora.ai), non-commercial unless separately licensed.
Contact
Editorial: editor@mediora.ai · Privacy/DSAR: privacy@mediora.ai
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。