Ncbi Entrez

Name: Ncbi Entrez
Author: beita6969

beita6969/scienceclaw

14 installs
869 repo stars
Updated June 8, 2026
beita6969/scienceclaw

ncbi-entrez is a skill that queries NCBI E-utilities to retrieve GenBank sequences, gene summaries, SNP and ClinVar variants, and cross-database links.

About

This skill documents how to query NCBI E-utilities to retrieve GenBank sequences, gene summaries, SNP and ClinVar variant data, and cross-database links. A researcher uses it to search a database for IDs and then fetch full records, using the two-step esearch plus efetch pattern. It specifies rate limits and an optional API key for higher throughput. It matters for bioinformatics workflows that pull authoritative sequence and variant data.

curl recipes for esearch, efetch, esummary, elink, and einfo E-utilities
Covers Gene, SNP, ClinVar, Nucleotide, Protein, OMIM, and PubMed databases
Rate limits: 3 req/s without a key, 10 req/s with NCBI_API_KEY

Ncbi Entrez by the numbers

14 all-time installs (skills.sh)
Ranked #1,388 of 2,065 Data Science & ML skills by installs in the Skillselion catalog
Data as of Aug 2, 2026 (Skillselion catalog sync)

At a glance

ncbi-entrez capabilities & compatibility

Free; optional NCBI_API_KEY raises throughput from 3 to 10 requests per second.

Capabilities: research · data analysis
Use cases: research · data analysis · api development
Pricing: Bring your own API key

From the docs

What ncbi-entrez says it does

Query NCBI E-utilities for GenBank sequences, gene info, SNPs, ClinVar variants, and literature links.

SKILL.md

Use esearch + efetch two-step pattern for bulk retrieval workflows.

SKILL.md

npx skills add https://github.com/beita6969/scienceclaw --skill ncbi-entrez

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/beita6969/scienceclaw/ncbi-entrez.svg)](https://skillselion.com/skills/beita6969/scienceclaw/ncbi-entrez)

Installs	14
repo stars	★ 869
Last updated	June 8, 2026
Repository	beita6969/scienceclaw ↗

What it does

Query NCBI E-utilities for gene, SNP, ClinVar, and GenBank sequence records via curl.

Who is it for?

Fetching gene, SNP, ClinVar, and GenBank sequence records and cross-database links from NCBI via curl.

Skip if: Protein annotations (use UniProt), 3D structures (use PDB), or pathway mapping (use KEGG).

When should I use this skill?

You need nucleotide or protein sequences, gene summaries, or variant data from NCBI databases.

What you get

The agent returns real gene, SNP, ClinVar, or sequence records from NCBI using the esearch plus efetch workflow.

By the numbers

7 supported databases
10 req/s with API key, 3 req/s without
retmax default 20, max 10000

Files

SKILL.mdMarkdownGitHub ↗

NCBI Entrez E-utilities API

Access NCBI databases (Gene, SNP, ClinVar, Nucleotide, Protein, OMIM) through the Entrez Programming Utilities. Supports search, fetch, linking, and summary operations.

API Endpoints

Base: https://eutils.ncbi.nlm.nih.gov/entrez/eutils

Authentication & Rate Limits

Set the NCBI_API_KEY environment variable for higher throughput.

With API key: 10 requests/second
Without API key: 3 requests/second

Append &api_key=$NCBI_API_KEY to all requests when available.

esearch.fcgi -- Search a database and return IDs

# Search for TP53 gene in human
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=gene&term=TP53[Gene]+AND+Homo+sapiens[Organism]&retmode=json"

# Search ClinVar for BRCA1 pathogenic variants
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=clinvar&term=BRCA1[gene]+AND+pathogenic[clinical_significance]&retmode=json&retmax=20"

# Search nucleotide database
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=nucleotide&term=SARS-CoV-2[Organism]+AND+complete+genome&retmode=json&retmax=5"

efetch.fcgi -- Retrieve full records by ID

# Fetch gene record for TP53 (Gene ID: 7157)
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=gene&id=7157&retmode=xml"

# Fetch nucleotide sequence in FASTA format
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nucleotide&id=NM_000546.6&rettype=fasta&retmode=text"

# Fetch SNP record
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=snp&id=rs1042522&retmode=json"

# Fetch ClinVar record in XML
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=clinvar&id=37653&rettype=clinvarset&retmode=xml"

esummary.fcgi -- Retrieve document summaries

# Get gene summary for TP53
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=gene&id=7157&retmode=json"

# Get summaries for multiple SNPs
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=snp&id=rs1042522,rs28897696&retmode=json"

elink.fcgi -- Cross-database linking

# Find SNPs linked to a gene
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=gene&db=snp&id=7157&retmode=json"

# Link gene to ClinVar entries
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=gene&db=clinvar&id=672&retmode=json"

# Find PubMed articles linked to a gene
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=gene&db=pubmed&id=7157&retmode=json"

einfo.fcgi -- List available databases and fields

# List all Entrez databases
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/einfo.fcgi?retmode=json"

# Get searchable fields for the gene database
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/einfo.fcgi?db=gene&retmode=json"

Supported Databases

Database	db= value	Description
Gene	`gene`	Gene records with summaries
SNP	`snp`	Single nucleotide polymorphisms
ClinVar	`clinvar`	Clinical variant interpretations
Nucleotide	`nucleotide`	GenBank nucleotide sequences
Protein	`protein`	GenBank protein sequences
OMIM	`omim`	Mendelian inheritance records
PubMed	`pubmed`	Biomedical literature

Common Patterns

# Two-step search + fetch workflow
# Step 1: Search for IDs
IDS=$(curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=gene&term=insulin[Gene]+AND+human[Organism]&retmode=json" | python3 -c "import sys,json; print(','.join(json.load(sys.stdin)['esearchresult']['idlist']))")

# Step 2: Fetch summaries for those IDs
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=gene&id=$IDS&retmode=json"

# Search with date range
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=clinvar&term=BRCA1[gene]&datetype=pdat&mindate=2024/01/01&maxdate=2025/12/31&retmode=json"

Best Practices

1. Always include &api_key=$NCBI_API_KEY when the env var is set for 10 req/s throughput. 2. Use retmode=json for easier parsing; fall back to retmode=xml when JSON is unavailable. 3. Use esearch + efetch two-step pattern for bulk retrieval workflows. 4. Respect rate limits strictly -- NCBI will block IPs that exceed them. 5. Use retmax to limit result counts (default is 20, max is 10000 for esearch). 6. Use elink to discover cross-database relationships (gene to SNP, gene to literature). 7. Include [Organism] qualifiers in search terms for species-specific results.

Data Integrity Rule

NEVER fabricate database results from training data. Every protein ID, gene name, compound property, pathway ID, structure detail, and metadata MUST come from an actual API response in this conversation. If the API returns no results, errors, or partial data, report exactly what happened. Do not "fill in" missing data from memory or make up identifiers.