NCBI-Datasets

This MCP server provides access to the NCBI Datasets ecosystem via 31 specialized tools organized into genome, gene, taxonomy, assembly, virus, protein, annotation, comparative genomics, sequence, phylogenetic, statistics, and quality control categories. Each tool accepts a structured set of arguments (e.g., identifiers, organism names, accession numbers, and filtering options) and returns data or data access URLs from the NCBI Datasets APIs. Use the provided resource templates to jump directly to common data types like genomes, genes, and taxonomy. If you supply an NCBI API key via the NCBI_API_KEY environment variable, you’ll benefit from higher rate limits and priority access.

To use a tool, send a JSON payload with the tool name and your arguments to the MCP server. For example, to search for genomes you would invoke the tool search_genomes with appropriate parameters, or to retrieve data for a specific genome you would call get_genome_info with an accession or ID. The server also offers batch and download-oriented operations (e.g., batch_assembly_info and download_genome_data) for higher throughput workflows.

Prerequisites:

• Node.js (LTS) and npm installed on your system
• Access to the project repository and build artifacts

Install and build steps:

1. Install dependencies npm install

2. Build the server npm run build

3. Run the MCP server (example) node /path/to/ncbi-datasets-server/build/index.js

4. Configure MCP to point to the running server (as shown in the Configuration section of the README) Edit your MCP settings to include the ncbi-datasets-server with the appropriate command, arguments, and any environment variables (e.g., NCBI_API_KEY).

Notes and tips:

• If you have an NCBI API key, set NCBI_API_KEY in the environment to improve rate limits (10 req/sec with priority). Without a key, you’ll be limited to baseline quotas.
• The server includes rate limiting and caching to optimize performance; monitor cache invalidation strategies if data freshness is critical.
• Use the resource templates (ncbi://genome/{accession}, ncbi://gene/{gene_id}, ncbi://taxonomy/{tax_id}, etc.) for direct data access paths in client applications.
• Ensure the build index.js path in the MCP configuration matches your deployment artifact location after running npm run build.
• For troubleshooting, check common parameter validation errors and ensure correct identifiers (accessions, tax IDs, gene IDs) are supplied.