{
  "markdown": "# Mediora.AI — MCP Server\n\nA hosted [Model Context Protocol](https://modelcontextprotocol.io) server that\nexposes **Mediora.AI**'s doctor-reviewed medical catalog to AI agents — blood-test\nmarkers, clinical conditions and patient symptoms — as callable tools, in\n**English, Russian and Hebrew**.\n\n- **Endpoint:** `https://mcp.mediora.ai/mcp` (JSON-RPC 2.0 over streamable HTTP)\n- **Discovery manifest:** `https://mcp.mediora.ai/.well-known/mcp.json`\n- **Human landing:** `https://mcp.mediora.ai/mcp/info`\n- **Website:** https://www.mediora.ai\n\n> This repository is the public **listing** for a **hosted** server. It contains the\n> registry manifest and connection instructions — not the server's source. Clients\n> connect to the endpoint above; there is nothing to run locally.\n\n## Connect\n\nAdd to your MCP client. For Claude Desktop (`claude_desktop_config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"mediora\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.mediora.ai/mcp\"\n    }\n  }\n}\n```\n\nNo API key is required for the catalog tools. Restart the client and ask, e.g.,\n*\"What does a high ferritin mean?\"* — the answer comes straight from Mediora's\ndoctor-reviewed catalog.\n\n## Tools\n\n### Anonymous — catalog reads (no token)\n\n| Tool | Returns |\n| --- | --- |\n| `mediora__list_markers` | Every blood-test marker (slug + short name) |\n| `mediora__explain_marker` | Full doctor-reviewed explainer for one marker |\n| `mediora__lookup_marker` | Fuzzy alias search across EN/RU/HE |\n| `mediora__list_conditions` | Every clinical condition (slug + ICD-10) |\n| `mediora__explain_condition` | Full explainer for a clinical condition |\n| `mediora__list_symptoms` | Every patient-side symptom |\n| `mediora__explain_symptom` | Symptom triage explainer with lab work-up |\n\n### Patient tools — require a Bearer JWT\n\n| Tool | Returns |\n| --- | --- |\n| `mediora__whoami` | The authenticated patient's profile summary |\n| `mediora__analyze_lab_pdf` | Upload a lab PDF/image for analysis (SSRF-guarded fetch) |\n| `mediora__get_patient_history` | The patient's uploaded tests |\n| `mediora__get_test_details` | A single test's markers + AI interpretation |\n| `mediora__longitudinal_trend` | A marker's trend across the patient's uploads |\n\n## What it is — and isn't\n\n- **Interpretation, not a diagnosis.** Mediora explains lab results; it never\n  produces a diagnosis or replaces a clinician.\n- **No PHI in the read surface.** The anonymous catalog tools carry no patient data.\n  Patient tools require the patient's own JWT and return only that patient's data.\n- **Doctor-reviewed.** Every catalog entry passes a 2-of-3 licensed-physician review\n  before it goes live.\n\n## Languages\n\nEnglish · Russian · Hebrew — native interpretation, not machine translation. Pass a\n`lang` argument (`en` | `ru` | `he`) to any catalog tool.\n\n## License\n\nThis repository (manifest + docs) is released under the [MIT License](LICENSE).\nThe catalog **content** served by the tools is licensed **CC-BY-NC 4.0** — free to\nuse with attribution to **Mediora.AI** (link to https://www.mediora.ai), non-commercial\nunless separately licensed.\n\n## Contact\n\nEditorial: editor@mediora.ai · Privacy/DSAR: privacy@mediora.ai\n",
  "bytes": 3179,
  "sha": "213b965638daff3242110c6b17b3659e1065bffde86c201a08c2c28e086a38ae",
  "repo_slug": "slatech-il/mediora-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_slatech_il_mediora_mcp_81f130ab/readme"
}