Raras Disease Twin — MCP Server

MCP serverDev tools

raras is a Disease Twin for Brazil: a structured map of knowledge covering 10,468 rare diseases, in Brazilian Portuguese. Once your AI has it, it can answer rare-disease questions using information grounded in documented sources. It is useful for researching rare diseases and how they relate to one another.

Use Raras Disease Twin — MCP Server in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Raras Disease Twin — MCP Server and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use Raras Disease Twin to search diseases

Details

Available today. Use it from your connected AI after setup.

Add raras, then ask your AI about a rare disease by name to see what it returns. Source code and documentation are at github.com/rarasai/raras.

Raras Disease Twin — MCP ServerStart free

What your AI can do with it

  • Answer questions about 10,468 rare diseases relevant to Brazil
  • Ground answers in documented sources
  • Search the rare-disease knowledge map
  • Explore how diseases relate to each other
  • Work in Brazilian Portuguese

Install Raras Disease Twin — MCP Server

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user raras-disease-twin-mcp-server 'https://raras.org/api/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://raras.org/api/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=raras-disease-twin-mcp-server&config=eyJ1cmwiOiJodHRwczovL3JhcmFzLm9yZy9hcGkvbWNwIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://raras.org/api/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add raras-disease-twin-mcp-server --url 'https://raras.org/api/mcp'

    Run it once, then sign in with codex mcp login raras-disease-twin-mcp-server if the server asks for an account.

From the project's README

As published by rarasai/raras in README.md.

Brazilian rare-disease knowledge graph (10,468 diseases) exposed via the Model Context Protocol (MCP). Each disease is an addressable Disease Twin (disease://{orphaCode}): genes, HPO phenotypes, SUS coverage, clinical trials, literature-mined treatments, repurposing hypotheses, and grounded multi-hop reasoning — PT-BR first, source-grounded, never diagnoses.

Connect (no install)

  • Remote endpoint: https://raras.org/api/mcp (Streamable HTTP, public, read-only)
  • Claude Code: claude mcp add --transport http raras https://raras.org/api/mcp
  • claude.ai / Desktop: Settings → Connectors → Add custom connector → paste the URL
  • Docs: https://raras.org/mcp

Skill

SKILL.md is an installable Claude Skill — drop it in .claude/skills/raras-disease-twin/.

License

Data: CC-BY-4.0 · Code: MIT · https://raras.org

Tools it offers (20)

What this server listed when Ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.

  • search_diseases
  • get_disease_detail
  • find_diseases_by_phenotypes
  • search_phenotypes
  • get_sus_coverage
  • find_reference_centers
  • find_active_trials
  • find_similar_diseases
  • find_phenotypically_similar
  • get_graph_stats
  • search_papers_semantic
  • find_papers_for_disease
  • analyze_clinical_case
  • get_schema
  • explain_relation
  • get_literature_relations
  • get_hypotheses
  • get_research_log
  • get_recent_updates
  • get_evidence

Signals

Last commit
May 2026
Advanced
Delivery
raras MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
io-github-rarasai-raras
Source
github.com/rarasai/raras
Hosted endpoint
https://raras.org/api/mcp