"How to improve memory or retention like GPT models" matching MCP servers:

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 enables language models to fetch protein information from the UniProt database, including protein details, sequences, functions, and structures.

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.

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.

Renders interactive 2D molecular structure diagrams from SMILES notation and computes molecular properties like molecular weight, LogP, and TPSA, directly in the chat.

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.

Phylogenetic inference server driving IQ-TREE 2, always returning per-clade bootstrap support plus model selection, tree comparison, and alignment simulation, with detailed diagnostics like conflicting clades and model uncertainty.

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.

An MCP server that enables AI coding assistants to interact with Rosetta, PyRosetta, and Biotite for running RosettaScripts, validating XML, translating between Rosetta and Biotite, scoring structures, and querying documentation.

Enables LLM agents to search biomedical literature, retrieve article details, find related papers, manage caching, and download open-access full texts through MCP with structured, agent-friendly responses.

Enables editing and querying of Gene Ontology Causal Activity Models (GO-CAMs) through the Barista API. Supports model creation, individual and fact management, evidence addition, and causal pathway construction for biological knowledge representation.

Enables AI assistants to rapidly gather and synthesize structural, chemical, conservation, and literature data about protein binding pockets for drug-target triage. Useful as a reconnaissance step before computational binder design.