NCBI E-utilities API

NCBI E-utilities provide programmatic access to the National Center for Biotechnology Information databases, including PubMed, GenBank, Gene, Protein, ClinVar, and SRA.

Evaluated Mar 06, 2026 (0d ago) vcurrent
Homepage ↗ Repo ↗ Other ncbi pubmed genbank bioinformatics genomics literature-mining rest-api entrez
⚙ Agent Friendliness
55
/ 100
Can an agent use this?
🔒 Security
61
/ 100
Is it safe for agents?
⚡ Reliability
68
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
75
Error Messages
62
Auth Simplicity
90
Rate Limits
70

🔒 Security

TLS Enforcement
100
Auth Strength
50
Scope Granularity
20
Dep. Hygiene
78
Secret Handling
65

Public scientific API — no sensitive data returned. API key is a simple query parameter (low security), but data is publicly available anyway. TLS enforced on all endpoints.

⚡ Reliability

Uptime/SLA
55
Version Stability
80
Breaking Changes
78
Error Recovery
58
AF Security Reliability

Best When

Building biomedical research agents that need to cross-reference literature (PubMed), sequences (GenBank), or clinical variants (ClinVar) from a single authoritative source.

Avoid When

You need to download millions of records in bulk — use NCBI FTP mirrors or Entrez Direct for bulk retrieval rather than the API.

Use Cases

  • Literature mining agents querying PubMed for research papers on a topic and extracting structured metadata
  • Genomics pipelines fetching DNA/protein sequences from GenBank or RefSeq by accession number
  • Clinical research agents querying ClinVar for known disease-associated variants
  • Drug discovery agents linking genes to pathways via NCBI Gene and cross-referencing publications
  • Automated submission monitoring for newly deposited sequences in SRA or nucleotide databases

Not For

  • High-throughput bulk downloads — use NCBI FTP or AWS Open Data snapshots instead
  • Real-time clinical decision support — data can lag by days for new submissions
  • Applications requiring guaranteed SLA — NCBI does not publish formal uptime guarantees

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
No
SDK
Yes
Webhooks
No

Authentication

Methods: api_key none
OAuth: No Scopes: No

API key optional but strongly recommended. Without key: 3 requests/sec limit. With key: 10 requests/sec. Key registration via NCBI account (free). Key passed as query parameter.

Pricing

Model: free
Free tier: Yes
Requires CC: No

Completely free public API funded by NIH. No paid tiers. Commercial use permitted with appropriate rate limit compliance.

Agent Metadata

Pagination
offset
Idempotent
Full
Retry Guidance
Not documented

Known Gotchas

  • Rate limits enforced per IP — agents must add delays between requests or register an API key
  • Responses are XML by default; JSON available for some endpoints via retmode=json but not all
  • ESearch returns UIDs that expire after 8 hours on NCBI history server — agents must use within the session
  • Large result sets require usehistory=y + WebEnv parameter chaining across ESearch/EFetch calls
  • Some databases (SRA) have much higher latency and may timeout for large queries
  • NCBI BLAST API is separate from E-utilities and has its own endpoint and RID polling pattern

Alternatives

Full Evaluation Report

Detailed scoring breakdown, competitive positioning, security analysis, and improvement recommendations for NCBI E-utilities API.

$99

Scores are editorial opinions as of 2026-03-06.

5178
Packages Evaluated
26151
Need Evaluation
173
Need Re-evaluation
Community Powered