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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.