Unified biomedical graph · MCP-native

One graph across
80+ biomedical databases.

BioBTree integrates genes, proteins, compounds, diseases, pathways and clinical data into a single queryable graph of 1.8 billion identifiers linked by ~10 billion connections, and serves it to LLMs through a native MCP server and to researchers through a REST API.

BRCA1>>ensembl>>uniprot>>pdb[resolution<2.0]

One line crosses three databases: find BRCA1, map it to UniProt proteins, return high-resolution PDB structures.

80+databases
1.8B+identifiers
10B+connections
MCPnative LLM access

What it is

Authoritative biomedical data, one query away

BioBTree mines primary databases, resolves their identifiers, and links everything into a single graph. Ask it in natural language, in one chained query, or over REST.

⛓️

Federated 1-line queries

Chain databases with >> and filter inline — no joins, no glue code. Search, map, and filter across every source.

🤖

Native MCP server

Grounds LLMs in structured, up-to-date biomedical data with reliable identifiers. Works with Claude, Codex, and Gemini CLIs.

🕸️

Biolink knowledge graph

A biolink-typed KGX export — categories, typed relationships, and evidence — ready for Neo4j. Explore it →

🔌

REST API & text search

Programmatic search / map / filter endpoints over the same graph that powers the MCP server.

🔄

80+ curated sources

Genes, proteins, structures, expression, variants, pathways, drugs, ontologies and clinical data — refreshed regularly.

📚

Powers Sugi Atlas

BioBTree is the engine behind Sugi Atlas — 52,000+ sourced reference pages on genes, drugs and diseases.

Try it

Connect in one step

The fastest way to experience BioBTree is through MCP. Point your AI client at the endpoint and ask in plain language.

MCP (recommended)

// add to your MCP client config
{
  "mcpServers": {
    "biobtree": {
      "type": "http",
      "url": "https://sugi.bio/biobtree/mcp"
    }
  }
}

Then just ask:

  • 💊 What tissues express SCN9A most highly?
  • 🧪 How many ClinVar variants does BRCA1 have, and how many are pathogenic?
  • 🎯 What are all the protein targets of Alectinib with IC50 values?

REST API

# search
https://sugi.bio/biobtree/api/search?i=BRCA1

# chained map across databases
.../api/map?i=BRCA1&m=>>ensembl>>uniprot>>chembl_target

# entry lookup
.../api/entry?i=P38398&s=uniprot

Or self-host the open-source engine — see the documentation.