"Using memory in programming with the Cursor system" matching MCP servers:

Control PyMOL from Cursor via natural language. Enables describing molecular structures and styles in plain language to execute PyMOL commands through XML-RPC.

Provides GPU-accelerated scientific computing capabilities including symbolic mathematics, quantum wave mechanics simulations, molecular dynamics, and neural network training through four specialized MCP servers.

Enables analysis of bulk RNA-seq data using natural language queries, executing R and Python in a Docker container with automatic sample anonymization and privacy controls.

Connects 3D Slicer with AI assistants through the Model Context Protocol, enabling medical image processing and scene manipulation using natural language.

Enables variant annotation and effect prediction using the Ensembl VEP API, with support for batch and single queries.

Enables querying gene expression experiments, brain region structure ontologies, and in-situ hybridization datasets from the Allen Institute's Brain Atlas public API.

Exposes the Adaptyv Foundry protein characterization API as MCP tools, enabling AI assistants to interact with experiments, targets, sequences, and results in natural language.

An MCP server for running local LLMs using llama-cpp-python, with built-in tools for generating drug-like molecule SMILES.

Enables AI agents to resolve marine species names to OBIS taxon records, retrieve georeferenced ocean occurrence records with optional date filtering, and pull aggregate statistics such as record counts, contributing datasets, and observed year ranges. Queries the Ocean Biodiversity Information System keylessly over the Pipeworx gateway or as a local stdio server.

Enables querying and retrieving bacterial and viral genomic data, features, antimicrobial resistance, and epitopes from the BV-BRC API using natural language.

Enables querying the Human Protein Atlas data using natural language or direct MCP tools, with keyless access via the Pipeworx gateway.

Validates the physical and chemical plausibility of ligand–protein docking poses using the PoseBusters tool.

Enables automated cell type annotation in scRNA-seq analysis using CellTypist models, with tools for listing, downloading, training, and annotating cell types via natural language.

Enables AI agents to retrieve and analyze breeding data from BrAPI-compliant databases through shared tools, with human-in-the-loop approval and verification.

Enables searching cryo-EM density maps in EMDB and raw datasets in EMPIAR, with filtering by resolution, keyword, and cross-referencing between the two databases.

Enables AI assistants to perform genomic variant analysis using OakVar, including running annotation pipelines, managing 200+ annotator modules, querying variant databases, and generating reports in various formats.

Reproduces the in-silico toxicological profile of Heracleum sosnowskyi metabolites from Rassabina & Fedorov (2025) using open-source models for LD50 prediction, toxicity classification, chemical space clustering, and synthesis cost estimation.

Runs the full HyphAeon report and per-pillar analyses in-process, with MEME concordance, over stdio or streamable HTTP.

Manages local protein experiments with a Flask backend and SQLite, offering tools for protein library management, Beer-Lambert concentration calculations, BLI dilution planning, and experiment archiving. It provides 7 MCP tools for AI assistants like Claude to interact with the system.

Enables protein structure prediction using the Chai-1 model via Docker, with tools for small peptides, FASTA-based predictions, MSA-enhanced predictions, batch processing, and job management.