Frontiers MCP server for AI agents
Let Claude, ChatGPT or your own agent read Frontiers: 2 typed functions through one MCP server. No Frontiers API key needed.
- Site
- frontiersin.org
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Frontiers
An MCP server for Frontiers alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/frontiersinEvery site
One MCP server for Frontiers and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
searchArticlesSearch Frontiers' open-access research articles by keyword, optionally within a publication date range; returns the match total and each article's…Arguments
Name Type Required argsstring | SearchArticlesArgsYes interface SearchArticlesArgs { /** words to search article titles, abstracts and keywords for */ query: string; /** default 10, max 50 */ limit?: number; offset?: number; /** "YYYY-MM-DD"; give with endDate (Frontiers refuses one without the other) */ startDate?: string; endDate?: string; }Returns
FrontiersArticleSearchinterface FrontiersArticle { articleId: number | null; doi: string | null; title: string | null; abstract: string | null; /** e.g. "22 Apr 2020"; null while accepted but not yet published */ publishedDate: string | null; acceptedDate: string | null; url: string | null; authors: { name: string; profileUrl: string | null }[]; journal: { id: number | null; title: string | null; abbreviation: string | null } | null; section: string | null; articleType: string | null; views: number | null; downloads: number | null; citations: number | null; } interface FrontiersArticleSearch { /** how many articles matched, across every page */ total: number; articles: FrontiersArticle[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/frontiersin/searchArticlesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.frontiersin.searchArticles({ query: "gut microbiome", limit: 3 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.frontiersin.searchArticles({"query": "gut microbiome", "limit": 3}))curl -X POST https://api.bowmark.ai/v1/sites/frontiersin/searchArticles \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"gut microbiome","limit":3}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.frontiersin.searchArticles({ query: "gut microbiome", limit: 3 });searchJournalsSearch Frontiers' journals (Frontiers in Neuroscience, Psychology, Immunology, …) by name or topic; returns each journal's link, ISSN, impact factor…Arguments
Name Type Required argsstring | SearchJournalsArgsYes interface SearchJournalsArgs { /** a journal name or topic, e.g. "neuroscience" */ query: string; /** default 10, max 50 */ limit?: number; offset?: number; }Returns
FrontiersJournalSearchinterface FrontiersJournal { id: number | null; title: string | null; url: string | null; slug: string | null; issn: string | null; impactFactor: string | null; citeScore: string | null; articleCount: number | null; viewCount: number | null; downloadCount: number | null; sectionCount: number | null; scope: string | null; } interface FrontiersJournalSearch { total: number; journals: FrontiersJournal[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/frontiersin/searchJournalsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.frontiersin.searchJournals({ query: "neuroscience", limit: 3 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.frontiersin.searchJournals({"query": "neuroscience", "limit": 3}))curl -X POST https://api.bowmark.ai/v1/sites/frontiersin/searchJournals \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"neuroscience","limit":3}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.frontiersin.searchJournals({ query: "neuroscience", limit: 3 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/frontiersin/<function> - OpenAPI
/v1/sites/frontiersin/openapi.json