This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
A unified biomedical graph database that integrates more than 95 public data sources (genes, proteins, compounds, diseases, pathways, and clinical data) into a single queryable graph of 3.5 billion entries linked by 9.3 billion cross-references. Its built-in MCP server gives LLMs direct access to structured, authoritative, up-to-date biomedical data.
BRCA1 >> ensembl >> uniprot >> pdb[resolution<2.0]One line, three databases: find BRCA1 in Ensembl, map to UniProt proteins, and return high-resolution PDB structures.
Website: sugi.bio/biobtree. Live MCP endpoint, REST API, examples, and full documentation.
BioBTree exports a biolink-typed KGX knowledge graph. A human-scoped, Neo4j-ready subgraph (~47M nodes / ~151M edges) is published on Zenodo under CC BY-NC-SA 4.0. See docs/kg_export.
Related MCP server: BioMCP
LLMs answering GeneTuring, LAB-Bench and variant questions with BioBTree, with web search and without tools: results in docs/benchmark.
BioBTree: An Integrated Biomedical Graph Database for Researchers and LLM Agents
Preprint (2026): https://doi.org/10.5281/zenodo.24144112
Earlier versions: preprint (Zenodo); BioBTree v1: Gür T, F1000Research 2019
Free for everyone. Use it live at sugi.bio, or self-host it under AGPL-3.0.
For commercial or closed-source use, a commercial license is available. Get in touch at contact@sugi.bio.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Open Targets MCP — disease/target/drug knowledge graph.
Monarch Initiative MCP — biomedical knowledge graph.
Knowledge graph ingestion, entity search, ontology analysis, and CoPass scoring.
Connect AI clients to biomedical data and tools.
