# io.github.SLAtech-IL/mediora-mcp

> Doctor-reviewed blood-test markers, conditions & symptoms as agent tools. EN/RU/HE. Hosted.

- name: io.github.SLAtech-IL/mediora-mcp
- version: 0.5.0
- connection class: R0 (autonomous)
- trust: 90/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.SLAtech-IL%2Fmediora-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.SLAtech-IL%2Fmediora-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "mediora-mcp": {
      "type": "http",
      "url": "https://mcp.mediora.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 65
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-96% ~updated-106d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: mediora__explain_marker (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); mediora__list_conditions (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); mediora__lookup_marker (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,147 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 14, about 2,147 tokens to load them all
- tool set hash: 3b983387cbd953e3965f196cbcc4a023
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.SLAtech-IL/mediora-mcp.svg)](https://protogrid.dev/servers/io.github.SLAtech-IL/mediora-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.mediora.ai/mcp (streamable-http, auth none, reachable true, uptime30d 0.9649123)

## Packages

_none_

## Tools (14)

- `mediora__analyze_lab_pdf`: Upload a lab-report PDF or scan (by HTTPS URL) and trigger Mediora.AI's full Vision + analysis pipeline. Returns a pending test id the client can poll. The URL must be https, must resolve to a public IP (no localhost / cloud-metadata / private LAN), and the file must be PDF / JPEG / PNG ≤ 10 MB. Redirects are not followed — pass the final URL.
- `mediora__explain_condition`: Return the full explainer for a clinical condition by slug. Includes: what the condition is, the key markers used in diagnosis, common symptoms, and when the patient should seek clinical evaluation.
- `mediora__explain_marker`: Return the full explainer for a single blood-test marker by slug. Includes: what it measures, what high/low values mean, when the value is clinically actionable, the conditions typically associated with it, and - where habits genuinely move the number - what can be done about a high or low result. Those action fields are empty when the value follows an underlying cause rather than lifestyle, which is itself the answer.
- `mediora__explain_panel`: Return the markers that make up a lab panel by slug — each resolved to its Mediora marker slug, name and one-line summary — plus the panel's search aliases (CBC/FBC, CMP, LFT, TFT, renal panel, …). Answers "what's included in a CBC / lipid panel / CMP". Follow each marker into mediora__explain_marker for full detail.
- `mediora__explain_symptom`: Return the full triage explainer for a single symptom by slug. Includes: what the symptom means, common causes, the lab work-up a clinician would order, and when the patient should seek urgent evaluation. The related marker and condition slug arrays let the upstream LLM follow the graph into mediora__explain_marker / explain_condition.
- `mediora__get_patient_history`: Return the patient's past medical-test rows (id, test type, test date, risk level, summary, status, abnormal-marker count). Bearer token must be a Mediora patient-scope JWT. Paginated; default 10 per page. Proxies https://api.mediora.ai/api/medical-tests with the user's token forwarded as Authorization: Bearer.
- `mediora__get_test_details`: Return the persisted markers + AI analysis (Summary, KeyFindings, Recommendations, DetailedExplanation) for a specific medical-test the authenticated patient owns. Use after mediora__get_patient_history surfaces a test id the user wants to discuss. Bearer token must be a Mediora patient-scope JWT. Proxies https://api.mediora.ai/api/medical-tests/{id} with the user's token forwarded as Authorization: Bearer.
- `mediora__list_conditions`: List every clinical condition in the Mediora catalog. Returns slug + name + ICD-10 code per entry. Use mediora__explain_condition for the full explainer.
- `mediora__list_markers`: List every blood-test marker in the Mediora catalog. Returns slug + short name per entry. Use mediora__explain_marker for the full explainer.
- `mediora__list_panels`: List every lab panel in the Mediora catalog (CBC, lipid, comprehensive metabolic, thyroid, iron, liver, kidney, diabetes, vitamin, inflammation, hormone, bone, cardiac, electrolyte, adrenal, PSA/prostate). Returns slug + name + marker count. Use mediora__explain_panel for the markers a panel contains.
- `mediora__list_symptoms`: List every patient-side symptom in the Mediora catalog (fatigue, joint pain, headache, etc.). Returns slug + short name. Use mediora__explain_symptom for the full triage-oriented explainer including the lab work-up a clinician would order.
- `mediora__longitudinal_trend`: Return the per-marker trajectory analyser output for the authenticated patient — HbA1c rising, eGFR falling, ferritin depleting, etc. Each finding includes the marker slug, kind, severity (Info / Notice / Important), trend per year, sample count, date range and a supportive headline + detail. Proxies https://api.mediora.ai/api/trajectory/warnings with the user's token forwarded as Authorization: Bearer.
- `mediora__lookup_marker`: Fuzzy-search markers by alias across EN/RU/HE. Useful when the upstream LLM has the lab's local name (e.g. "гликированный гемоглобин", "המוגלובין מסוכרר", "A1C") and needs to find the canonical Mediora slug.
- `mediora__whoami`: Validate a Mediora.AI patient Bearer token and return the patient id + email it represents. Use this first to confirm the token before calling other auth-gated tools. The token is obtained by going through the standard Mediora.AI login at https://www.mediora.ai — the same JWT the browser stores in localStorage as 'auth_token'.