Index / MCP servers / io.github.rarasAI/raras

io.github.rarasAI/raras MCP server

io.github.rarasAI/raras is an MCP server with 20 tools an agent can call, among them analyze_clinical_case, explain_relation, find_active_trials. It answers at https://raras.org/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 23 October 2026, succeeded.

Status

Answering

Tools

Reliability

6 of 6 checks

Response time

1164 ms

Transport

streamable HTTP

Last checked

23 October 2026

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

Description as the publisher wrote it.

The 20 tools io.github.rarasAI/raras offers

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

Add io.github.rarasAI/raras to your AI client

Every block below points at https://raras.org/api/mcp. Pick your client and copy.

Claude Code: one command in your terminal

claude mcp add --transport http io-github-rarasai-raras https://raras.org/api/mcp

Claude Desktop: claude_desktop_config.json

{
  "mcpServers": {
    "io-github-rarasai-raras": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://raras.org/api/mcp"]
    }
  }
}

Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

{
  "mcpServers": {
    "io-github-rarasai-raras": {
      "url": "https://raras.org/api/mcp"
    }
  }
}

VS Code and GitHub Copilot: .vscode/mcp.json

{
  "servers": {
    "io-github-rarasai-raras": {
      "type": "http",
      "url": "https://raras.org/api/mcp"
    }
  }
}

Zed: Zed settings.json

{
  "context_servers": {
    "io-github-rarasai-raras": {
      "url": "https://raras.org/api/mcp"
    }
  }
}

Windsurf: ~/.codeium/mcp_config.json

{
  "mcpServers": {
    "io-github-rarasai-raras": {
      "serverUrl": "https://raras.org/api/mcp"
    }
  }
}

JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON

{
  "mcpServers": {
    "io-github-rarasai-raras": {
      "url": "https://raras.org/api/mcp"
    }
  }
}

Continue: .continue/mcpServers/neuronto.yaml

name: io.github.rarasAI/raras
version: 0.0.1
schema: v1
mcpServers:
  - name: io.github.rarasAI/raras
    type: streamable-http
    url: https://raras.org/api/mcp

Gemini CLI: ~/.gemini/settings.json

{
  "mcpServers": {
    "io-github-rarasai-raras": {
      "httpUrl": "https://raras.org/api/mcp"
    }
  }
}

Codex CLI: MCP server config

{
  "mcpServers": {
    "io-github-rarasai-raras": {
      "type": "http",
      "url": "https://raras.org/api/mcp"
    }
  }
}

Warp: MCP servers, + Add, paste JSON

{
  "mcpServers": {
    "io-github-rarasai-raras": {
      "url": "https://raras.org/api/mcp"
    }
  }
}

Goose: a one-click extension link

goose://extension?url=https%3A%2F%2Fraras.org%2Fapi%2Fmcp&type=streamable_http&id=io-github-rarasai-raras&name=io.github.rarasAI/raras

Is io.github.rarasAI/raras up right now?

It answered our last check on 23 October 2026 in 1164 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to io.github.rarasAI/raras

Opentargets43 tools Medius Docs5 tools Health Data4 tools IBGE Brasil23 tools Brazil Macro AI0 tools Meelion5 tools

Questions about io.github.rarasAI/raras

How many tools does io.github.rarasAI/raras have?

20, as returned by the server's own tools/list on 20 September 2026: analyze_clinical_case, explain_relation, find_active_trials, find_diseases_by_phenotypes, find_papers_for_disease, find_phenotypically_similar, find_reference_centers, find_similar_diseases, and 12 more.

Is io.github.rarasAI/raras down?

It answered our last check on 23 October 2026 in 1164 ms. Over 6 checks since 11 September 2026 it answered 6.

How do I add io.github.rarasAI/raras to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://raras.org/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does io.github.rarasAI/raras need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: io.github.rarasai. Endpoint host: raras.org. ARD identifier: urn:air:io.github.rarasai:mcp:raras. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.