sirusb samtools mcp

A Model Control Protocol implementation for SAMtools, providing a standardized interface for working with SAM/BAM/CRAM files.

• View and convert SAM/BAM/CRAM files
• Sort alignment files
• Index BAM/CRAM files
• Generate statistics
• Merge multiple BAM files
• Calculate read depth
• Index FASTA files
• And more...

• File Format Support: Handle SAM (text), BAM (binary), and CRAM (compressed) alignment files
• Format Conversion: Convert between SAM, BAM, and CRAM formats seamlessly
• Region-Specific Analysis: Extract and analyze specific genomic regions
• Flag-Based Filtering: Filter reads based on SAM flags
• Performance Optimization: Multi-threaded operations for sorting and merging
• Statistical Analysis: Generate comprehensive alignment statistics

The easiest way to use SAMtools MCP is through Docker:

# Pull the Docker image
docker pull nadhir/samtools-mcp:latest

# Run the container
docker run -it --rm nadhir/samtools-mcp:latest

# To process BAM files, mount a volume:
docker run -it --rm -v /path/to/your/bam/files:/data nadhir/samtools-mcp:latest

1. Clone the repository:

git clone https://github.com/your-username/samtools_mcp.git
cd samtools_mcp

1. Install dependencies:

pip install uv
uv pip install -r requirements.txt

To configure the MCP server to use the Docker image, add the following to your MCP configuration file:

{
  "servers": {
    "samtools": {
      "type": "docker",
      "image": "nadhir/samtools-mcp:latest",
      "volumes": [
        {
          "source": "/path/to/your/data",
          "target": "/data"
        }
      ]
    }
  }
}

To configure the MCP to run using uv, add the following to your ~/.cursor/mcp.json:

{
  "samtools_mcp": {
    "command": "uv",
    "args": ["run", "--with", "fastmcp", "fastmcp", "run", "/path/to/samtools_mcp.py"]
  }
}

Replace /path/to/samtools_mcp.py with the actual path to your samtools_mcp.py file.

1. View BAM file:

from samtools_mcp import SamtoolsMCP

mcp = SamtoolsMCP()
result = mcp.view(input_file="/data/example.bam")

1. Sort BAM file:

result = mcp.sort(input_file="/data/example.bam", output_file="/data/sorted.bam")

1. Index BAM file:

result = mcp.index(input_file="/data/sorted.bam")

1. View specific region with flags:

result = mcp.view(
    input_file="/data/example.bam",
    region="chr1:1000-2000",
    flags_required="0x2",
    output_format="SAM"
)

1. Sort by read name:

result = mcp.sort(
    input_file="/data/example.bam",
    output_file="/data/namesorted.bam",
    sort_by_name=True
)

1. Calculate depth with multiple input files:

result = mcp.depth(
    input_files=["/data/sample1.bam", "/data/sample2.bam"],
    region="chr1:1-1000000"
)

Contributions are welcome! Please feel free to submit a Pull Request.

This project is licensed under the MIT License - see the LICENSE file for details.