PubMed Search

Search PubMed biomedical literature: title, authors, journal, date, DOI, PMC id and link. Supports PubMed field syntax and date ranges.

Pay by wallet (x402) pubmed-search

Example

Example answer

{
  "query": "crispr",
  "articles": [
    {
      "doi": "10.1111/febs.13110",
      "url": "https://pubmed.ncbi.nlm.nih.gov/25315507/",
      "pmid": "25315507",
      "issue": "23",
      "pages": "5186-93",
      "title": "Genome modification by CRISPR/Cas9.",
      "pmc_id": null,
      "volume": "281",
      "authors": [
        "Ma Y"
      ],
      "journal": "The FEBS journal",
      "pub_date": "2014 Dec",
      "epub_date": "2014 Nov 7",
      "languages": [
        "eng"
      ],
      "journal_abbrev": "FEBS J",
      "publication_types": [
        "Journal Article"
      ]
    }
  ],
  "returned": 1,
  "total_results": 70584
}

Inputs

Field	Type	Required	What it is
`sort`	string	No	relevance (default) or date
`limit`	integer	No	Results to return, 1-20. Default: 10
`query`	string	Yes	Search terms; PubMed field tags such as crispr[Title] AND 2024[dp] are accepted
`max_date`	string	No	Latest publication date as YYYY, YYYY/MM or YYYY/MM/DD
`min_date`	string	No	Earliest publication date as YYYY, YYYY/MM or YYYY/MM/DD

Output fields

How reliably each field appears in a successful answer.

Field	Type	Appears
`query`	string	Always (present in every successful answer)
`articles`	array	Always (present in every successful answer)
`returned`	number	Always (present in every successful answer)
`total_results`	number	Always (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "pubmed-search",
    "inputs": {
      "query": "crispr cas9 genome editing",
      "limit": 3
    },
    "max_price_cents": 3
  }'

{
  "tool": "strale_execute",
  "arguments": {
    "slug": "pubmed-search",
    "inputs": {
      "query": "crispr cas9 genome editing",
      "limit": 3
    },
    "max_price_cents": 3
  }
}

import { Strale } from "straleio";

const strale = new Strale({ apiKey: process.env.STRALE_API_KEY! });
const result = await strale.do({
  capability_slug: "pubmed-search",
  inputs: {
    "query": "crispr cas9 genome editing",
    "limit": 3
  },
  max_price_cents: 3,
});

import os
from straleio import Strale, DoRequest

strale = Strale(api_key=os.environ["STRALE_API_KEY"])
result = strale.do(DoRequest(
    capability_slug="pubmed-search",
    inputs={
        "query": "crispr cas9 genome editing",
        "limit": 3,
    },
    max_price_cents=3,
))

# No account. The first request answers 402 with the price in USDC;
# an x402 client pays it from your wallet and repeats the request.
curl -i -X POST https://api.strale.io/x402/v2/pubmed-search \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "crispr cas9 genome editing",
    "limit": 3
  }'

Limitations

Returns citation metadata only, not abstracts or full text
NCBI's summary endpoint carries title, authors, journal and identifiers. Abstracts require a second fetch that this capability does not perform.
What to do instead: Pass the returned DOI to paper-details for the abstract and open-access link.
Two requests per call share a 3-request-per-second limit
Sustained bursts trip NCBI's limiter; the error is surfaced as retryable and nothing is cached.
What to do instead: Space calls out or raise limit to fetch more per call.