ZBS Index What actually exists in applied AI, with the source next to it

mcp server

raras

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

Description as published by the maintainer. Source

  • version 0.2.0
  • active
  • memory and context

active — Registry entry last updated 2026-05-21. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

21 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

analyze_clinical_case(papers_limit, diseases_limit, case_description)
Caso clínico → doenças candidatas + literatura relevante em 1 chamada. Apenas informativo, nunca diagnóstico. Required: case_description.
explain_relation(query, hpo_ids, max_hops)
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. Required: query.
find_active_trials(limit, orphaCode, in_brazil_only)
Trials ativos com filtro Brazil. Required: orphaCode.
find_communities(limit, orphaCode)
Comunidades FEBRARARAS por doença. Required: orphaCode.
find_diseases_by_phenotypes(limit, hpo_ids)
Match por IDs HPO. Use para diagnóstico diferencial. Required: hpo_ids.
find_papers_for_disease(limit, min_score, orphaCode)
Literatura relacionada a uma doença via embeddings (:SEMANTIC_MATCH, fallback vetorial). Required: orphaCode.
find_phenotypically_similar(limit, orphaCode)
Doenças com perfil de fenótipos HPO semelhante (simGIC pré-computado, explicável: nº de fenótipos em comum). Complementa find_similar_diseases (semântico). Required: orphaCode.
find_reference_centers(limit, state, orphaCode)
Centros por doença e/ou UF, com CNES.
find_similar_diseases(limit, orphaCode)
Vector similarity via embeddings SOTA. Required: orphaCode.
get_disease_detail(orphaCode)
Fenótipos HPO, genes, SUS, trials, descrição clínica em PT. Required: orphaCode.
get_evidence(orphaCode)
Cross-references de autoridade (Orphanet, MONDO, OMIM, MeSH, GARD, UMLS), status de verificação e PMIDs de uma doença. A base da regra "nunca inventar". Required: orphaCode.
get_graph_stats
Contagens e métricas do dataset.
get_hypotheses(orphaCode)
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). Required: orphaCode.
get_literature_relations(orphaCode, predicate)
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. Required: orphaCode.
get_recent_updates(days, limit)
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).
get_research_log(orphaCode)
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. Required: orphaCode.
get_schema
Node labels, relationship types e property keys do grafo. Use antes de cypher_query.
get_sus_coverage(orphaCode)
CEAF, SIGTAP, PNTN, nível de integração. Required: orphaCode.
search_diseases(limit, query, filter_has_sus_coverage, filter_has_active_trials)
Full-text search em 10.468 doenças raras. Suporta filtros SUS/trials. Required: query.
search_papers_semantic(limit, query, min_score)
Busca vetorial sobre 424k papers do PubMed. Use caso clínico, pergunta ou conjunto de sintomas. Required: query.
search_phenotypes(limit, query)
Lookup HPO em PT ou EN. Retorna IDs HP:. Required: query.

Last successful function declaration observed on . Source: https://raras.org/api/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://raras.org/api/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
Latest published version 0.2.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-05-21 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-05-21 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
mcp tools declared 21 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe raras.org
mcp endpoint status ok The server listed 21 functions when asked. as of probe raras.org

Where to get it

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Tools declared by the MCP server at https://raras.org/api/mcp — raras.org, observed , trust tier 1.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.