"A tool for indexing or searching codebases" matching MCP servers:

Provides an MCP interface to the ROBOT command-line tool for OWL ontology editing, enabling operations like merging, reasoning, and conversion via natural language.

Enables genomic sequence analysis through the Evo 2 model, supporting DNA sequence scoring, embedding, generation, and variant effect prediction with multiple model checkpoints (7B, 40B, 1B parameters).

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

This server enables multi-agent conversations for interacting with Cirro's biological data platform through its OpenAPI interface, auto-generated using AG2's MCP builder.

Provides access to EMBL-EBI bioinformatics data including InterPro domains, Pfam families, protein features, and taxonomy through a unified tool.

A production-ready Model Context Protocol (MCP) server that provides comprehensive access to the BioOntology API for searching, annotating, and exploring over 1,200 biological ontologies.

Enables searching ENA's public sequencing data by organism, study, platform, country or date, retrieving FASTQ/BAM download URLs and checksums, and discovering available result types and fields.

Enables AI agents to search public cancer genomics studies (TCGA, CPTAC, MSK, and more), fetch full details for individual studies, resolve gene symbols to Entrez ids, and list cancer types. Works keylessly against open cBioPortal data over a hosted MCP endpoint, a local stdio server, or plain HTTP.

Enables searching a manually curated database of stable macromolecular protein complexes by protein or complex name, gene, GO term, or biological process, and fetching individual records by accession to retrieve subunits with UniProt identifiers, biological roles, and stoichiometry. Complements UniProt, IntAct, and STRING, and can be used keyless over a hosted gateway endpoint or run locally over stdio.

MCP server for querying the GWAS Catalog (EBI/NHGRI), a curated catalog of genome-wide association studies. It enables AI agents to search and retrieve study data via natural language or direct tool calls.

Enables searching and retrieving cancer-genomics projects, cases, and genomic data files — including TCGA, TARGET, and CPTAC — via keyless, open-access metadata tools. Supports filtering by primary site, project, or data category, and can route plain-English questions to the right tool automatically.

Enables AI assistants to perform DNA/RNA sequence alignment using BWA (Burrows-Wheeler Aligner), supporting both short and long read alignment to reference genomes with indexing, BWA-MEM, and BWA-backtrack algorithms.

Enables searching cancer genes and curated variants from CIViC, retrieving associated diseases, therapies, and graded evidence items and assertions for clinical interpretation.

Connects to NCBI E-utilities for searching, fetching, and linking biological data across Entrez databases.

Enables querying of the Monarch Initiative biomedical knowledge graph for genes, diseases, phenotypes, and their associations through natural language or direct tool calls.

This server provides access to InterPro protein family, domain, and functional-site classification data from EBI. It allows querying protein annotations through natural language or direct tool calls.

Federates 13 gene-related MCP backends (gnomAD, GTEx, etc.) behind a single Streamable HTTP endpoint with collision-free namespacing and search-based tool discovery.

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

Provides MCP tool adapters for Bioconductor methods like limma, DESeq2, and fgsea, enabling statistical analysis of omics data through containerized R execution. It serves as a bridge between MCP clients and bioinformatics tools for reproducible research workflows.

Enables AI agents to look up molecular interactions from the EBI IntAct database by gene/protein name or UniProt ID, returning detection method, interaction type, organism, PubMed reference, and MI confidence score, along with fast interaction counts. It is keyless and available either through a hosted MCP endpoint, a plain HTTP API, or a local stdio server.