Nextstrain Tools#

Configuration File: nextstrain_tools.json Tool Type: Local Tools Count: 2

This page contains all tools defined in the nextstrain_tools.json configuration file.

Available Tools#

Nextstrain_get_dataset (Type: NextstrainTool)#

Get metadata and phylogenetic summary for a Nextstrain pathogen dataset. Returns title, last upda…

Nextstrain_get_dataset tool specification

Tool Information:

  • Name: Nextstrain_get_dataset

  • Type: NextstrainTool

  • Description: Get metadata and phylogenetic summary for a Nextstrain pathogen dataset. Returns title, last update date, number of sequences, data provenance, maintainers, root node attributes, and available coloring options. Useful for understanding the scope and currency of pathogen genomic surveillance data. Example: ‘zika’ returns 1044 sequences tracking Zika virus evolution, last updated Dec 2025.

Parameters:

  • dataset (string) (required) Nextstrain dataset path. Examples: ‘zika’, ‘ebola’, ‘flu/seasonal/h3n2/ha/2y’, ‘dengue/denv1’, ‘mpox/clade-IIb’.

Example Usage:

query = {
    "name": "Nextstrain_get_dataset",
    "arguments": {
        "dataset": "example_value"
    }
}
result = tu.run(query)

Nextstrain_list_datasets (Type: NextstrainTool)#

List available pathogen phylogenetic datasets from Nextstrain. Returns datasets grouped by pathog…

Nextstrain_list_datasets tool specification

Tool Information:

  • Name: Nextstrain_list_datasets

  • Type: NextstrainTool

  • Description: List available pathogen phylogenetic datasets from Nextstrain. Returns datasets grouped by pathogen (e.g., avian-flu, dengue, ebola, flu, measles, mpox, SARS-CoV-2, zika), each with its true ‘dataset_count’. By default only the first 10 dataset paths per pathogen are listed; when that hides entries the response sets ‘truncated’: true with a ‘truncation_note’, and ‘metadata.total_datasets’ always reports the full catalogue size (not the number listed). Pass datasets_per_pathogen=0 to list every dataset. Optionally filter by pathogen name. Nextstrain provides real-time molecular epidemiology for public health, tracking how pathogens evolve and spread worldwide.

Parameters:

  • pathogen ([‘string’, ‘null’]) (optional) Optional pathogen name filter. Examples: ‘flu’, ‘ebola’, ‘zika’, ‘dengue’, ‘mpox’. Leave empty for all pathogens.

  • datasets_per_pathogen ([‘integer’, ‘null’]) (optional) Maximum number of dataset paths listed per pathogen (default 10). Set to 0 to list every dataset with no cap, or to a larger number (e.g. 100) to cover the biggest pathogens such as ncov and avian-flu.

Example Usage:

query = {
    "name": "Nextstrain_list_datasets",
    "arguments": {
    }
}
result = tu.run(query)