# io.usefulapi/infermedica (remote · infermedica.usefulapi.io)

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

- Trust score: 76/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-04

## Components

- remote · `infermedica.usefulapi.io`: 76/100 (this document), [markdown](https://verifymcp.io/servers/io-usefulapi-infermedica/infermedica.md), [page](https://verifymcp.io/servers/io-usefulapi-infermedica/infermedica)

## Channel facts

- Endpoint: `https://infermedica.usefulapi.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-04.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2471 tokens (~145/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the io.usefulapi/infermedica MCP server?

io.usefulapi/infermedica is a hosted endpoint at https://infermedica.usefulapi.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-usefulapi-infermedica 'https://infermedica.usefulapi.io/mcp'
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "io-usefulapi-infermedica": {
      "type": "http",
      "url": "https://infermedica.usefulapi.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-usefulapi-infermedica]
url = "https://infermedica.usefulapi.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-usefulapi-infermedica": {
      "type": "remote",
      "url": "https://infermedica.usefulapi.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-usefulapi-infermedica --url 'https://infermedica.usefulapi.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-usefulapi-infermedica:
    url: "https://infermedica.usefulapi.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-usefulapi-infermedica": {
      "Transport": "http",
      "Url": "https://infermedica.usefulapi.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-usefulapi-infermedica -t streamable-http -u 'https://infermedica.usefulapi.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-usefulapi-infermedica": {
      "type": "http",
      "url": "https://infermedica.usefulapi.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-03 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-02 (score 75, 0)

- [functional] Server version: 1.3.0 → 1.5.1

### 2026-10-01 (score 75, +5)

- [security improvement] HTTPS: unverified → pass
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.0.0 → 1.3.0

### 2026-09-30 (score 70, +42)

- [security improvement] Authorization: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] First check of Authorization: partial
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 95
- [functional] First check of Schema quality: good

### 2026-09-29 (score 28)

First indexed and scored.

## MCP tools (17)

### `infermedica_list_symptoms` (~131 tokens)

List symptoms

List all symptoms in the Infermedica medical model (optionally age-filtered). Engine API: GET /symptoms.

Input parameters:

- `age` (object): Optional age filter (returns only age-relevant symptoms).
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `enable_triage_5` (boolean): If true, include symptoms only used by the 5-level triage model.
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_get_symptom` (~112 tokens)

Get symptom

Get a single symptom by its id. Engine API: GET /symptoms/{id}.

Input parameters:

- `age` (object): Optional age context.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `id` (string, required): Symptom id, e.g. 's_21' (required).
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_list_conditions` (~95 tokens)

List conditions

List all conditions (diseases) in the Infermedica medical model. Engine API: GET /conditions.

Input parameters:

- `age` (object): Optional age filter.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_get_condition` (~109 tokens)

Get condition

Get a single condition by its id. Engine API: GET /conditions/{id}.

Input parameters:

- `age` (object): Optional age context.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `id` (string, required): Condition id, e.g. 'c_87' (required).
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_list_risk_factors` (~96 tokens)

List risk factors

List all risk factors in the Infermedica medical model. Engine API: GET /risk_factors.

Input parameters:

- `age` (object): Optional age filter.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_get_risk_factor` (~115 tokens)

Get risk factor

Get a single risk factor by its id. Engine API: GET /risk_factors/{id}.

Input parameters:

- `age` (object): Optional age context.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `id` (string, required): Risk factor id, e.g. 'p_28' (required).
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_list_lab_tests` (~98 tokens)

List lab tests

List all lab tests (and their results) in the Infermedica medical model. Engine API: GET /lab_tests.

Input parameters:

- `age` (object): Optional age filter.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_get_lab_test` (~113 tokens)

Get lab test

Get a single lab test by its id. Engine API: GET /lab_tests/{id}.

Input parameters:

- `age` (object): Optional age context.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `id` (string, required): Lab test id, e.g. 'lt_1' (required).
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_search_concepts` (~154 tokens)

Search concepts

Search the medical concept database for observations matching a phrase (autocomplete). Engine API: GET /search.

Input parameters:

- `age` (object): Optional age filter.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `max_results` (integer): Maximum number of results to return (default 8).
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.
- `phrase` (string, required): Text phrase to match against concept names/synonyms (required).
- `sex` (string): Optional sex filter.
- `types` (array): Restrict results to these concept types.

### `infermedica_get_info` (~98 tokens)

Get model info

Get metadata about the current Infermedica medical model (version, last update, concept counts). Engine API: GET /info.

Input parameters:

- `age` (object): Optional age context.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.

### `infermedica_diagnosis` (~187 tokens)

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.

Input parameters:

- `age` (object, required): Patient age, e.g. { value: 30 } or { value: 6, unit: 'month' }.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `evidence` (array): Evidence collected so far (may be empty for the first call).
- `extras` (object): Optional engine flags (e.g. disable_groups, enable_triage_5).
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.
- `sex` (string, required): Patient biological sex.

### `infermedica_triage` (~183 tokens)

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.

Input parameters:

- `age` (object, required): Patient age, e.g. { value: 30 } or { value: 6, unit: 'month' }.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `evidence` (array): List of observed evidence (symptoms / risk factors / lab tests) and their states.
- `extras` (object)
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.
- `sex` (string, required): Patient biological sex.

### `infermedica_explain` (~188 tokens)

Explain condition

Explain which evidence supports or conflicts with a given target condition, for the collected evidence. Non-mutating computation. Engine API: POST /explain.

Input parameters:

- `age` (object, required): Patient age, e.g. { value: 30 } or { value: 6, unit: 'month' }.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `evidence` (array): List of observed evidence (symptoms / risk factors / lab tests) and their states.
- `extras` (object)
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.
- `sex` (string, required): Patient biological sex.
- `target` (string, required): Target condition id to explain, e.g. 'c_49' (required).

### `infermedica_suggest` (~207 tokens)

Suggest observations

Suggest additional symptoms/observations the patient is likely to have, to speed up the interview. Non-mutating computation. Engine API: POST /suggest.

Input parameters:

- `age` (object, required): Patient age, e.g. { value: 30 } or { value: 6, unit: 'month' }.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `evidence` (array): List of observed evidence (symptoms / risk factors / lab tests) and their states.
- `extras` (object)
- `max_results` (integer): Maximum number of suggestions.
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.
- `sex` (string, required): Patient biological sex.
- `suggest_method` (string): Which kind of observations to suggest (default 'symptoms'). Sent as the `suggest_method` query param.

### `infermedica_rationale` (~164 tokens)

Get question rationale

Explain WHY the diagnostic engine wants to ask its next question, given the evidence. Non-mutating computation. Engine API: POST /rationale.

Input parameters:

- `age` (object, required): Patient age, e.g. { value: 30 } or { value: 6, unit: 'month' }.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `evidence` (array): List of observed evidence (symptoms / risk factors / lab tests) and their states.
- `extras` (object)
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.
- `sex` (string, required): Patient biological sex.

### `infermedica_parse` (~234 tokens)

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.

Input parameters:

- `age` (object, required): Patient age, e.g. { value: 30 } or { value: 6, unit: 'month' }.
- `concept_types` (array): Restrict captured mentions to these concept types.
- `context` (array): Ordered ids of already-captured present symptoms, used as parsing context.
- `correct_spelling` (boolean): If true, correct spelling of the input before analysis.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `include_tokens` (boolean): If true, include tokenization details in the output.
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.
- `sex` (string, required): Patient biological sex.
- `text` (string, required): Free-text describing the patient's complaints (required).

### `infermedica_recommend_specialist` (~187 tokens)

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.

Input parameters:

- `age` (object, required): Patient age, e.g. { value: 30 } or { value: 6, unit: 'month' }.
- `dev_mode` (boolean): If true, mark the request as test traffic → sends the `Dev-Mode: true` header.
- `evidence` (array): List of observed evidence (symptoms / risk factors / lab tests) and their states.
- `extras` (object): Optional flags (e.g. a specialist_mapping remap).
- `model_id` (string): Optional medical model id → sent as the `Model-Id` request header.
- `sex` (string, required): Patient biological sex.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-usefulapi-infermedica/infermedica#diagnostics

## Score history

- 2026-10-04: 76
- 2026-10-03: 76
- 2026-10-02: 75
- 2026-10-01: 75
- 2026-09-30: 70
- 2026-09-29: 28

## Common questions

### What is the io.usefulapi/infermedica MCP server?

io.usefulapi/infermedica is an MCP server listed in the public MCP registry as io.usefulapi/infermedica. Run Infermedica symptom checks, diagnosis, triage and condition lookups. This page covers its hosted endpoint (https://infermedica.usefulapi.io/mcp).

### Is the io.usefulapi/infermedica MCP server safe to use?

io.usefulapi/infermedica scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.usefulapi/infermedica MCP server expose?

io.usefulapi/infermedica exposes 17 tools: infermedica_list_symptoms, infermedica_get_symptom, infermedica_list_conditions, infermedica_get_condition, infermedica_list_risk_factors, and 12 more. Their descriptions and schemas cost roughly 2,471 tokens of context every time the server is loaded.

### Does the io.usefulapi/infermedica MCP server require authentication?

Yes. io.usefulapi/infermedica asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the io.usefulapi/infermedica MCP server still maintained?

io.usefulapi/infermedica is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://infermedica.usefulapi.io/mcp
- Repository: https://github.com/m190/usefulapi-mcp
- Changelog RSS feed: https://verifymcp.io/servers/io-usefulapi-infermedica/infermedica.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-usefulapi-infermedica/infermedica.json
- HTML version of this page: https://verifymcp.io/servers/io-usefulapi-infermedica/infermedica