# io.github.rarasAI/raras (remote · raras.org)

Disease Twin — Brazil's rare-disease knowledge graph (10,468) over MCP. Source-grounded, PT-BR.

- Trust score: 67/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `raras.org`: 67/100 (this document), [markdown](https://verifymcp.io/servers/rarasai-raras/api-mcp.md), [page](https://verifymcp.io/servers/rarasai-raras/api-mcp)

## Channel facts

- Endpoint: `https://raras.org/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## 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 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 21 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1222 tokens (~58/item across 21 items; 21 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (33% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http rarasai-raras https://raras.org/api/mcp
```

### Codex

```toml
[mcp_servers.rarasai-raras]
url = "https://raras.org/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "rarasai-raras": {
      "type": "remote",
      "url": "https://raras.org/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add rarasai-raras --url https://raras.org/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  rarasai-raras:
    url: "https://raras.org/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "rarasai-raras": {
      "type": "http",
      "url": "https://raras.org/api/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.

### 2026-08-03 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 65, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 64, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 63, +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.

### 2026-07-27 (score 62, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 61)

First indexed and scored.

## MCP tools (21)

### `search_diseases` (~65 tokens)

Buscar doenças raras

Full-text search em 10.468 doenças raras. Suporta filtros SUS/trials.

Input parameters:

- `filter_has_active_trials` (boolean)
- `filter_has_sus_coverage` (boolean)
- `limit` (integer)
- `query` (string, required)

### `get_disease_detail` (~37 tokens)

Detalhes de doença rara

Fenótipos HPO, genes, SUS, trials, descrição clínica em PT.

Input parameters:

- `orphaCode` (string, required)

### `find_diseases_by_phenotypes` (~41 tokens)

Buscar doenças por fenótipos

Match por IDs HPO. Use para diagnóstico diferencial.

Input parameters:

- `hpo_ids` (array, required)
- `limit` (integer)

### `search_phenotypes` (~38 tokens)

Buscar fenótipos HPO

Lookup HPO em PT ou EN. Retorna IDs HP:.

Input parameters:

- `limit` (integer)
- `query` (string, required)

### `get_sus_coverage` (~35 tokens)

Cobertura SUS

CEAF, SIGTAP, PNTN, nível de integração.

Input parameters:

- `orphaCode` (string, required)

### `find_reference_centers` (~44 tokens)

Centros de referência

Centros por doença e/ou UF, com CNES.

Input parameters:

- `limit` (integer)
- `orphaCode` (string)
- `state` (string)

### `find_active_trials` (~41 tokens)

Ensaios clínicos ativos

Trials ativos com filtro Brazil.

Input parameters:

- `in_brazil_only` (boolean)
- `limit` (integer)
- `orphaCode` (string, required)

### `find_similar_diseases` (~35 tokens)

Doenças similares

Vector similarity via embeddings SOTA.

Input parameters:

- `limit` (integer)
- `orphaCode` (string, required)

### `find_phenotypically_similar` (~73 tokens)

Doenças com fenótipos similares

Doenças com perfil de fenótipos HPO semelhante (simGIC pré-computado, explicável: nº de fenótipos em comum). Complementa find_similar_diseases (semântico).

Input parameters:

- `limit` (integer)
- `orphaCode` (string, required)

Output parameters:

- `method` (string)
- `orphaCode` (string)
- `results` (array)

### `find_communities` (~35 tokens)

Comunidades de pacientes

Comunidades FEBRARARAS por doença.

Input parameters:

- `limit` (integer)
- `orphaCode` (string, required)

### `get_graph_stats` (~17 tokens)

Estatísticas do grafo

Contagens e métricas do dataset.

### `search_papers_semantic` (~56 tokens)

Busca semântica de papers

Busca vetorial sobre 424k papers do PubMed. Use caso clínico, pergunta ou conjunto de sintomas.

Input parameters:

- `limit` (integer)
- `min_score` (number)
- `query` (string, required)

### `find_papers_for_disease` (~53 tokens)

Papers de uma doença

Literatura relacionada a uma doença via embeddings (:SEMANTIC_MATCH, fallback vetorial).

Input parameters:

- `limit` (integer)
- `min_score` (number)
- `orphaCode` (string, required)

### `analyze_clinical_case` (~57 tokens)

Analisar caso clínico

Caso clínico → doenças candidatas + literatura relevante em 1 chamada. Apenas informativo, nunca diagnóstico.

Input parameters:

- `case_description` (string, required)
- `diseases_limit` (integer)
- `papers_limit` (integer)

### `get_schema` (~27 tokens)

Esquema do grafo

Node labels, relationship types e property keys do grafo. Use antes de cypher_query.

### `explain_relation` (~120 tokens)

Explicar relação (MedGraphRAG, raciocínio multi-hop)

Raciocínio fundamentado sobre o grafo: dada uma pergunta (ex.: "por que o gene X se associa à doença Y?", "como a droga Z se relaciona a esta doença?"), retorna caminhos de evidência multi-hop (doença↔gene↔via↔droga↔fenótipo) com proveniência citável. Se não houver caminho no grafo, recusa — nunca inventa.

Input parameters:

- `hpo_ids` (array)
- `max_hops`
- `query` (string, required)

Output parameters:

- `hasEvidence` (boolean)
- `paths` (array)
- `query` (string)
- `summary` (object)

### `get_literature_relations` (~79 tokens)

Relações mineradas da literatura (PubTator3)

Relações tipadas extraídas da literatura biomédica (associate/treat/cause/inhibit/stimulate/prevent) entre a doença e genes/fármacos, com nº de publicações como proveniência. Filtrável por predicado.

Input parameters:

- `orphaCode` (string, required)
- `predicate` (string)

Output parameters:

- `orphaCode` (string)
- `relations` (array)
- `source` (string)

### `get_hypotheses` (~87 tokens)

Hipóteses de reposicionamento (co-scientist)

Candidatos a reposicionamento de fármacos gerados por associação de genes (guilt-by-association): drogas que tratam outras doenças que compartilham genes com esta. HIPÓTESES para investigação, NUNCA recomendações clínicas — cada uma rastreável (via gene X, da doença Y).

Input parameters:

- `orphaCode` (string, required)

Output parameters:

- `hypotheses` (array)
- `isRecommendation` (boolean)
- `method` (string)
- `name` (string)
- `orphaCode` (string)

### `get_research_log` (~74 tokens)

Diário de pesquisa do Disease Twin

Registro cronológico do que o agente autônomo fez por esta doença: autoria, mineração de literatura, evidência genética, verificação, prospecção de fontes, recomputação de relações. Prova de que o gêmeo digital estuda a doença continuamente.

Input parameters:

- `orphaCode` (string, required)

Output parameters:

- `events` (array)
- `name` (string)
- `orphaCode` (string)

### `get_recent_updates` (~69 tokens)

Disease Twins atualizados recentemente

Doenças cujo gêmeo digital ganhou evidência nova (autoria, PubTator3, Open Targets, verificação) nos últimos N dias. Faça polling para acompanhar mudanças (substituto stateless de subscriptions).

Input parameters:

- `days` (integer)
- `limit` (integer)

Output parameters:

- `sinceDays` (number)
- `updates` (array)

### `get_evidence` (~64 tokens)

Proveniência / evidências

Cross-references de autoridade (Orphanet, MONDO, OMIM, MeSH, GARD, UMLS), status de verificação e PMIDs de uma doença. A base da regra "nunca inventar".

Input parameters:

- `orphaCode` (string, required)

Output parameters:

- `diseaseTwin` (object)
- `name`
- `neverInvent` (boolean)
- `orphaCode` (string)
- `pmids` (array)
- `verification` (object)
- `xrefs` (object)

## Diagnostics

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

## Score history

- 2026-08-03: 67
- 2026-08-02: 66
- 2026-08-01: 66
- 2026-07-31: 65
- 2026-07-30: 64
- 2026-07-29: 63
- 2026-07-28: 62
- 2026-07-27: 62
- 2026-07-26: 61

## Links

- Remote endpoint: https://raras.org/api/mcp
- Repository: https://github.com/rarasAI/raras
- Website: https://raras.org/mcp
- Changelog RSS feed: https://verifymcp.io/servers/rarasai-raras/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/rarasai-raras/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/rarasai-raras/api-mcp