BioPython

You run BioPython MCP Server to expose BioPython’s rich bioinformatics capabilities through the Model Context Protocol, enabling AI-assisted workflows and conversational access to sequence analysis, alignments, database queries, structure insights, and phylogenetics. This server lets you perform complex analyses from natural language interfaces and integrate them into automated pipelines with minimal friction.

How to use

Operate the BioPython MCP Server from your MCP client by starting a local server and pointing your client at the appropriate command. You can run the server directly for quick experiments or configure it in your client’s MCP setup to keep it running in the background.

How to install

Prerequisites: Python 3.10 or higher and a package manager compatible with your environment (uvx, pip). You will run the server either with uvx for a zero-install start or install the package locally for a persistent setup.

# Quick start with uvx (no installation needed)
uvx biopython-mcp

# Or run directly from source after cloning
git clone https://github.com/kmaneesh/biopython-mcp.git
cd biopython-mcp
uvx --from . biopython-mcp
```} ,{

Additional configuration and usage notes

Configure your MCP client to connect to BioPython MCP Server. You can set up one or more MCP connections in your Claude Desktop or other MCP client configuration files.

{
  "mcpServers": {
    "biopython": {
      "command": "uvx",
      "args": ["biopython-mcp"],
      "env": {
        "NCBI_EMAIL": "you@example.com",
        "NCBI_API_KEY": "your_ncbi_api_key"
      }
    }
  }
}
```}]} ,{

Environment and startup details

The server relies on environment variables for NCBI access. You can provide your contact email and an optional API key to increase NCBI rate limits.

export NCBI_EMAIL="your.email@example.com"
export NCBI_API_KEY="your_api_key_here"
````}]} ,{

Examples of typical workflows

Fetch a GenBank sequence, analyze GC content, translate to protein, and perform motif searches from an MCP-enabled client.

# Pseudocode for a typical workflow via MCP client
fetch_genbank(accession="NM_000207", email="user@example.com")
ccalculate_gc_content(sequence="ATGGCC...")
translate_sequence(sequence="ATGGCC...")
find_motif(sequence="ATGGCC...", motif="ATG")
````}]}]} ,{

Tools and capabilities overview

BioPython MCP Server exposes a broad set of tools across multiple domains. You can translate sequences, compute GC content, perform alignments, fetch database records, analyze structures, and construct phylogenetic trees.

Available tools

translate_sequence

Translate DNA/RNA to protein sequences using standard genetic code or custom codon tables.

reverse_complement

Compute the reverse complement of DNA sequences.

transcribe_dna

Transcribe DNA to RNA according to the transcription rules.

calculate_gc_content

Calculate GC percentage of a given nucleotide sequence.

find_motif

Search for motifs or patterns within a sequence.

pairwise_align

Compute global or local alignments between two sequences.

multiple_sequence_alignment

Align multiple sequences simultaneously.

calculate_alignment_score

Score alignments using a chosen substitution matrix.

fetch_genbank

Retrieve GenBank records by accession number.

fetch_uniprot

Retrieve UniProt entries for proteins.

search_pubmed

Query PubMed for related literature.

fetch_sequence_by_id

Get sequences by a given identifier.

fetch_pdb_structure

Download and parse PDB structures.

calculate_structure_stats

Compute statistics on protein or nucleic acid structures.

find_active_site

Identify active site residues within a structure.

build_phylogenetic_tree

Construct phylogenetic trees from sequence data.

calculate_distance_matrix

Compute distance matrices for a set of sequences.

draw_tree

Visualize phylogenetic trees.