usefulapi

Infermedica MCP server. Run Infermedica symptom checks, diagnosis, triage and condition lookups.

Claude

Open Settings → Connectors → Add custom connector
Paste this URL:
https://infermedica.usefulapi.io/mcp
Authenticate with Infermedica when prompted

Cursor · VS Code · Windsurf · Cline

Add to your MCP config, then reload & authorize:

{
  "mcpServers": {
    "infermedica": {
      "url": "https://infermedica.usefulapi.io/mcp"
    }
  }
}

live17 toolsFree 100 tool calls / monthPro $9/mo · $90/yr

Tools 17

Tool	Type	What it does
`infermedica_list_symptoms`	read	List symptoms List all symptoms in the Infermedica medical model (optionally age-filtered). Engine API: GET /symptoms.
`infermedica_get_symptom`	read	Get symptom Get a single symptom by its id. Engine API: GET /symptoms/{id}.
`infermedica_list_conditions`	read	List conditions List all conditions (diseases) in the Infermedica medical model. Engine API: GET /conditions.
`infermedica_get_condition`	read	Get condition Get a single condition by its id. Engine API: GET /conditions/{id}.
`infermedica_list_risk_factors`	read	List risk factors List all risk factors in the Infermedica medical model. Engine API: GET /risk_factors.
`infermedica_get_risk_factor`	read	Get risk factor Get a single risk factor by its id. Engine API: GET /risk_factors/{id}.
`infermedica_list_lab_tests`	read	List lab tests List all lab tests (and their results) in the Infermedica medical model. Engine API: GET /lab_tests.
`infermedica_get_lab_test`	read	Get lab test Get a single lab test by its id. Engine API: GET /lab_tests/{id}.
`infermedica_search_concepts`	read	Search concepts Search the medical concept database for observations matching a phrase (autocomplete). Engine API: GET /search.
`infermedica_get_info`	read	Get model info Get metadata about the current Infermedica medical model (version, last update, concept counts). Engine API: GET /info.
`infermedica_diagnosis`	read	Compute diagnosis Run the diagnostic engine over the collected evidence — returns the next question to ask, ranked candidate conditions with probabilities, and a should_stop flag. Non-mutating computation. Engine API: POST /diagnosis.
`infermedica_triage`	read	Compute triage Recommend a triage level (emergency_ambulance \| emergency \| consultation_24 \| consultation \| self_care) plus any serious/emergency observations, given the evidence. Non-mutating computation. Engine API: POST /triage.
`infermedica_explain`	read	Explain condition Explain which evidence supports or conflicts with a given target condition, for the collected evidence. Non-mutating computation. Engine API: POST /explain.
`infermedica_suggest`	read	Suggest observations Suggest additional symptoms/observations the patient is likely to have, to speed up the interview. Non-mutating computation. Engine API: POST /suggest.
`infermedica_rationale`	read	Get question rationale Explain WHY the diagnostic engine wants to ask its next question, given the evidence. Non-mutating computation. Engine API: POST /rationale.
`infermedica_parse`	read	Parse clinical text Extract clinical mentions (symptoms / risk factors) and their states from free-text describing complaints, mapping them to Infermedica evidence ids (NLP). Non-mutating computation. Engine API: POST /parse.
`infermedica_recommend_specialist`	read	Recommend specialist Recommend the most appropriate medical specialist and consultation channel for the collected evidence (accepts the same body as diagnosis/triage). Non-mutating computation. Engine API: POST /recommend_specialist.

Pricing

Plan	Price	Limit
Free	$0	100 tool calls / month
Pro	$9/mo · $90/yr	Unlimited

This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.