MCP Servers / web-scraping / mcp-techtrend

mcp-techtrend

httpnone★ 1web-scraping

Multi-source MCP server: arXiv + PubMed + GitHub + HuggingFace + openFDA 510(k)/Recalls. Newspaper-style briefings, per-domain tuning, sandbox-safe Python launcher.

github ↗

Install

How to run this server

[ { "cmd": "pip install -r", "imports": [] } ]

server path: mcp-techtrend

Tools

What this server exposes

arxiv_recent

Recent papers in one category, by submission date

arxiv_search

Keyword / field-syntax search (ti:, au:, abs:, cat:)

pubmed_search

PubMed search (MeSH terms, field tags) — abstracts via efetch

paperswithcode_trending

HF Daily Papers, sorted by community upvotes

github_trending

Browse github.com/trending (HTML scrape)

github_search

GitHub Search API; days filters by created:

huggingface_trending

HF Hub models / datasets / spaces

fda_510k_recent

Recent FDA 510(k) clearances

fda_recalls_recent

Recent FDA medical-device recalls (class filter)

trends_digest

Multi-source bullet-list digest, given a topic

trends_briefing

Multi-source newspaper briefing; topic optional

trends_get_config

Show current settings (token values never returned)

trends_set_enabled_sources

Toggle which sources are active

trends_set_arxiv_categories

Set arXiv categories + per-category weights

trends_set_pubmed_query

Set the default PubMed query

trends_set_token

Set / clear a rate-limit booster token

Configuration

Environment & auth

authnone

envGITHUB_TOKEN

envNCBI_API_KEY

envOPENFDA_API_KEY

Resources

githubhttps://github.com/salwks/mcp-techTrend ↗