BWA (Burrows-Wheeler Aligner)

An MCP server for the BWA sequence alignment tool.

MCP (Model Context Protocol) server for the BWA (Burrows-Wheeler Aligner) sequence alignment tool.

This MCP server provides access to BWA functionality, allowing AI assistants to perform alignment of short and long sequencing reads to a reference genome.

- bwa_index: Create an index for a reference genome.
- bwa_mem: Align reads using the BWA-MEM algorithm.
- bwa_aln: Find SA coordinates with the BWA-backtrack algorithm.
- bwa_samse: Generate single-end alignments in SAM format.
- bwa_sampe: Generate paired-end alignments in SAM format.
- Support for large reference genomes and read files.

# macOS brew install bwa # Ubuntu/Debian sudo apt-get install bwa # From conda conda install -c bioconda bwa

git clone https://github.com/bio-mcp/bio-mcp-bwa cd bio-mcp-bwa pip install -e .

Add to your MCP client configuration (e.g., Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.json):

{ "mcpServers": { "bio-bwa": { "command": "python", "args": ["-m", "src.server"], "cwd": "/path/to/bio-mcp-bwa" } } }

- BIO_MCP_MAX_FILE_SIZE: Maximum input file size in bytes (default: 50GB)
- BIO_MCP_TIMEOUT: Command timeout in seconds (default: 3600)
- BIO_MCP_BWA_PATH: Path to BWA executable (default: finds in PATH)
- BIO_MCP_TEMP_DIR: Temporary directory for processing

Once configured, the AI assistant can use the following tools:

Create a BWA index for a reference genome.

- reference_fasta(required): Path to the reference FASTA file.
- algorithm: Indexing algorithm (bwtsworis). Defaults tobwtswfor genomes >2GB.

Align reads using the BWA-MEM algorithm.

- reference(required): Path to the indexed reference genome.
- reads1(required): Path to the first reads file (FASTQ).
- reads2: Path to the second reads file for paired-end alignment.
- threads: Number of threads to use (default: 4).
- min_seed_length: Minimum seed length (default: 19).
- band_width: Band width for banded alignment (default: 100).
- read_group: Read group header line.

Find SA coordinates with the BWA-backtrack algorithm.

- reference(required): Path to the indexed reference genome.
- reads(required): Path to the reads file (FASTQ).
- threads: Number of threads to use (default: 4).
- max_mismatches: Maximum number of mismatches (default: 4).
- max_gap_opens: Maximum number of gap opens (default: 1).

Generate alignments in SAM format for single-end reads.

- reference(required): Path to the indexed reference genome.
- sai_file(required): Path to the .sai file frombwa_aln.
- reads(required): Path to the original reads file.

Generate alignments in SAM format for paired-end reads.

- reference(required): Path to the indexed reference genome.
- sai_file1(required): Path to the .sai file for read 1.
- sai_file2(required): Path to the .sai file for read 2.
- reads1(required): Path to the reads file 1.
- reads2(required): Path to the reads file 2.

Create a BWA index for the file hg38.fasta.

Align the paired-end reads from r1.fastq and r2.fastq to the hg38 reference genome using BWA-MEM.

Control anaerobic digestion modeling (ADM1) using natural language.

Bioinformatics data for AI agents — gene search, protein structures, clinical variants, PubMed literature, and DNA sequences via NCBI and UniProt. No API key required.

MCP server for generating, scoring and embedding genomic sequences using Evo 2

Interact with Omics AI Explorer networks for genomics research and data analysis.

Real-time access to 1000 Genomes Project dataset

Rosetta protein design & modeling for agents

Access and interact with Allen Institute for Neural Dynamics (AIND) metadata directly within your IDE.

A high-performance JavaScript server for the Alliance of Genome Resources (AGR) MCP.

Access the AlphaFold Protein Structure Database for protein structure prediction and analysis.