"Using npx to run tools directly without requiring an API" matching MCP servers:

Enables MCP-capable AI clients to characterize proteins end to end: PDB/mmCIF validation, sequence extraction and typing, pLDDT confidence summaries, metal-site geometry with bidentate chelate detection, GROMACS trajectory metrics and plots, and live UniProt, AlphaFold DB, and RCSB lookups. Also ships a point-and-click Protein Lab web UI (and a persistent run registry) so students and wet-lab biologists can get the same results without any client setup.

Enables AI agents to query Human Phenotype Ontology clinical phenotype terms, navigate term hierarchies, and retrieve gene-disease and disease-phenotype annotations through keyless MCP tools.

Provides a collection of MCP servers for computational chemistry tasks including molecular generation and retrosynthesis. Also offers property prediction and molecule pricing capabilities.

Enables deep probabilistic analysis of single-cell omics data using scvi-tools through natural language. Supports SCVI for scRNA-seq analysis, SCANVI for cell type annotation, TOTALVI for multi-modal RNA/protein data, and PEAKVI for scATAC-seq analysis.

A specialized MCP server for Metal-Organic Framework research that provides tools for database searching, structural optimization, and energy calculations via ASE. It enables scientific workflows by allowing users to interact with MOF data and perform chemical simulations through a standard SSE interface.

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 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.

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.

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 gives Claude access to NCBI Datasets v2 — search genome assembly metadata, retrieve taxonomy records, and download data packages without leaving your conversation.

An MCP server that provides tools for searching and fetching protein data from the UniProt database using the unipressed library.

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

Parses MS-DIAL binary lipidomics outputs and runs standard analyses server-side, returning compact summaries so an LLM can drive full lipidomics analysis without exposing raw matrices.

Enables AI assistants to access protein information directly from UniProt, allowing retrieval of protein names, functions, sequences, and organism data by accession number.

Allows to retrieve information about an AnnData object via MCP using the read_lazy function from anndata.

An MCP server that enables single-cell RNA sequencing analysis through natural language, supporting data processing, visualization, and analysis tasks without requiring coding knowledge.

Enables querying and accessing hivtools data through a REST API and MCP-compatible tools.

Bridge any AI coding assistant directly to GenePattern — run bioinformatics modules, manage cloud jobs, and stream results, all through natural language.

An MCP server that enables AI assistants to generate, score, and analyze DNA sequences using the evo2 genomic foundation model. It supports multiple execution modes including local GPU, SLURM clusters, and the Nvidia NIM cloud API for tasks like variant effect prediction and sequence embedding.

An MCP server that exposes the KEGG REST API — pathways, genes, compounds, reactions, enzymes, diseases, drugs, modules, orthology, glycans, and BRITE hierarchies, with cross-database linking. Provides 34 tools and 8 resource templates.

Enables AI agents to search EBI BioSamples metadata for biological samples such as cell lines, tissues, and organisms by free-text keyword, and to fetch individual records by accession to retrieve taxId, organism, and characteristics like tissue, sex, and cell type. It can run as a hosted gateway endpoint or locally over stdio via npx.

Exposes pipen bioinformatics pipelines as MCP tools, allowing AI assistants to discover and run complex workflows through a progressive disclosure interface.

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

Exposes 25 stdio-based tools for SnapGene-style DNA work, letting agents inspect plasmids, find restriction sites, digest, clone, run PCR, design primers, mutate sequences, auto-annotate features, verify sequencing reads and find CRISPR guides. All file access is sandboxed to a configurable root directory and every operation is available both as a CLI command with JSON output and as an MCP tool.

Enables LLM agents to design proteins, predict structures, score interfaces, and run molecular dynamics simulations through a unified interface.

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

Enables users to list templates, create and build structure-biology figures, render protein structures, and run QA and palette checks through seven tools backed by structfig.

Enables LLM agents to route bioinformatics tool calls through pre-run checks that block known silent-error traps and return one-line fixes before commands execute.

Enables AI agents to browse the Gene Ontology through the EBI QuickGO API, including keyword search for GO terms, retrieval of a term's name, aspect, definition and synonyms by id, and listing the GO annotations tied to a UniProt accession. Runs keyless over HTTP or as a local stdio server, with an optional gateway route that lets plain-English questions be answered without choosing tools manually.

Enables AI assistants to query VirtualFlyBrain data, run queries, and search for terms related to Drosophila neurobiology.

Enables AI assistants to generate publication-quality bioinformatics visualizations (volcano plots, PCA, heatmaps, etc.) directly from raw biological data.

MCP server for biological protein design, folding, and affinity prediction using Refua tools, with optional support for ADMET, clinical simulation, preclinical planning, wet-lab automation, and more.

An MCP server that gives LLM agents access to computational protein design tools.

Enables Claude and other MCP clients to run fast, exactly scored similarity and substructure searches over a local PubChem fingerprint index, pull live PubChem records (identifiers, synonyms, GHS, bioassays) with cited sources, and compute offline RDKit descriptors, med-chem alerts and highlighted structure drawings — all without API rate limits.

Enables AI agents to resolve scientific (Latin binomial) names to Open Tree of Life taxon IDs, retrieve full taxonomic details, synonyms, and ancestor lineages, and find the most recent common ancestor of up to 10 taxa within the synthetic tree of life. Runs keylessly over a hosted gateway endpoint or locally via npx.

Enables LLMs to run rule-based molecular interaction simulations using the Kappa language through the Kappybara package. Returns simulation results as CSV data for analysis of biochemical systems and molecular binding dynamics.

Enables discovery and querying of public OpenBind structure-affinity datasets, experimental binding events, benchmark results, and live Fragalysis targets and observations through read-only REST endpoints without requiring an API key.

BioOpenMCP enables users to run bioinformatics tools like FastQC, Cutadapt, and STAR with background execution and status checking. It integrates with Claude Desktop to perform quality control, trimming, alignment, and reporting via natural language.

A self-driving cheminformatics MCP server that dynamically exposes a growing library of RDKit-based molecular analysis tools (fingerprints, descriptors, substructure matching, drug-likeness filters, and more) as MCP tools, with each skill autonomously implemented and tested by an agent loop without human intervention.