"How to build your own knowledge base" matching MCP servers:

Run real bioinformatics from your AI agent on your own GPUs: MMseqs2 homology search, ESMFold structure prediction and sequence tools for Claude, Cursor and Codex. GPU-aware scheduling for shared machines, fail-fast input checks, background jobs, agent-friendly results and provenance for every run.

Enables querying HERB 2.0's Traditional Chinese Medicine knowledge base for herbs, ingredients, gene targets, diseases, PubMed-cited papers, and GEO transcriptomic experiments, with each relationship tagged by evidence tier.

Enables querying metadata from MyVariant.info, a comprehensive variant annotation database, providing dataset statistics, source information, and build versions.

Provides access to UniProt protein sequence and function knowledge base, enabling search and retrieval of protein entries, proteomes, taxonomy, and feature annotations.

Enables LLMs and AI agents to query a biomedical knowledge graph stored in RedisGraph, with tools for concept search, synonym enrichment, and study variable discovery through semantic relationships.

Enables querying and retrieving cell line records from the Cellosaurus knowledge base via its REST API, including searching, fetching by accession, and accessing release information.

Enables language models to search biomedical literature, fetch sequences, and follow links across Entrez databases through eleven read-only tools wrapping the nine NCBI Entrez E-utilities. It handles URL building, pacing, redirects, response caps, and API-key redaction so queries can be answered without a browser or scraping.

Grounds gene-nomenclature work in the HUGO Gene Nomenclature Committee (HGNC) dataset, enabling resolution of gene symbols and IDs to canonical HGNC identifiers, plus cross-references and batch operations.

Enables AI assistants to clean PDB structures and run initial-stage energy relaxation for biomolecular modeling. It provides a structured workflow for preparing structures before production molecular dynamics or coarse-graining pipelines.

MCP server that provides tools to query harmonized gene-disease validity data from the Gene Curation Coalition, supporting consensus and conflict detection for gene-disease assertions.

Enables coding agents to interact with the Reactome pathway database, including search, lookup, hierarchy traversal, SBML/SBGN export, and gene-set enrichment analysis.

Provides direct SQL access to a locally hosted Reactome database, enabling schema discovery, guarded read-only queries, and ergonomic helpers over the full relational schema.

Guides researchers, including those new to BPP, from raw sequence data to a validated control file that has passed a short test run. Wraps BPP command-line tools without running long analyses itself.

A Model Context Protocol (MCP) server for interacting with Gen3 data commons, with GraphQL query validation to reduce hallucinations.

Provides read-only access to the ProPaths verified protein interactome, letting AI agents search proteins, retrieve mechanistic interaction details, and explore pathway ontology through MCP tools, resources, and prompts.

Empowers AI agents with direct access to the official ClinicalTrials.gov database, enabling programmatic searching, retrieval, and analysis of clinical study data through a Model Context Protocol interface.

A Model Context Protocol server that interfaces with Biomart databases, allowing models to discover biological datasets, explore attributes/filters, retrieve biological data, and translate between different biological identifiers.

An MCP server that provides mouse genetics data from Mouse Genome Informatics (MGI), enabling LLM agents to query markers, mutations, alleles, phenotypes, and disease models.

MCP server that exposes the UniProt REST API to LLM clients, enabling search and retrieval of protein data via tools like search_uniprotkb, get_entry, and map_ids.

Enables AI assistants to run reproducible bioinformatics pipelines over MCP, with verifiable provenance via checksums and Workflow Run RO-Crate metadata.