Skip to main content
Glama

Frontier: evidence-scored science breakthroughs

Server Details

New papers from Nature, Science, Cell, NEJM and other top journals, scored on evidence and novelty.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a clearly distinct operation: explaining the methodology, fetching one entry, listing recent entries, listing fields, and searching the index. The only near-overlap is between latest_breakthroughs and search_breakthroughs (empty query browse), but their descriptions cleanly separate recency-based listing from query-based search.

Naming Consistency4/5

Consistent snake_case with a verb_noun leaning (explain_frontier_score, get_breakthrough, list_fields, search_breakthroughs). The lone deviation is latest_breakthroughs, which uses an adjective rather than a verb, but the pattern remains highly readable.

Tool Count5/5

Five tools is well-scoped for a read-only discovery server over a curated index. Each tool covers a distinct facet (methodology, single entry, recency, taxonomy, search) with no filler.

Completeness4/5

The surface covers the core discovery workflow: browse fields, list recent, search, and drill into a single entry, plus score explanations. Minor gaps exist (no direct browse by author/institution or explicit pagination control), but these are workable via search.

Available Tools

5 tools
explain_frontier_scoreHow the Frontier Score worksB
Read-onlyIdempotent
Inspect

The Frontier Score method: its three pillars and what each measures, recency, the integrity rule, tiers and confidence.

Inputs: no named parameters.

get_breakthroughOne entry in fullA
Read-onlyIdempotent
Inspect

Everything Frontier holds on one entry: the plain-language summary, why it matters and what to watch, authors and institutions, the full Frontier Score breakdown (each pillar and what drives it, recency and confidence) and the sources behind each figure. Accepts an OpenAlex work id (e.g. W7214802080), an entry slug, or a frontierresearch.co entry URL.

Inputs: id (required).

latest_breakthroughsLatest scored breakthroughsA
Read-onlyIdempotent
Inspect

What Frontier added most recently: the entries listed in the last N days (the index adds a few new papers from the top journals every day), newest first, optionally within one field.

Inputs: days, field, limit.

list_fieldsFields in the indexA
Read-onlyIdempotent
Inspect

The research fields Frontier covers, with how many entries each holds and its median Frontier Score.

Inputs: no named parameters.

search_breakthroughsSearch scored breakthroughsA
Read-onlyIdempotent
Inspect

Search Frontier's evidence-scored index of new research from the top scientific journals. Matches the query against titles, plain-language summaries, authors and topics, optionally within one field, and returns the matching entries ranked by Frontier Score (or newest paper first), each with its summary, score, Frontier URL and DOI. Leave the query empty to browse a field.

Inputs: sort, field, limit, query.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      B
      maintenance
      Your AI's research copilot. Searches 6 academic databases, downloads real PDFs, reads them cover to cover, extracts evidence, renders figures, syncs to Zotero.
      16
      16
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables scientific due diligence by grading claims against public literature, clinical trials, and filings, with explicit citations and optional attestation.
      4
      MIT
    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables auditing scientific papers for methodological biases such as selection bias and p-hacking, and assessing citation credibility and research consensus.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables assistants and editors to query a curated, read-only evidence graph for graded findings about what compounds, supplements, nutrients and foods have been shown to do in the human body, each with an automatic A–F grade, the verbatim source sentence, paper, population, dose and a permalink, plus reference-database relations labelled as hypotheses. It also exposes no products, prices or purchase links, and returns no medical advice or rankings of what to take.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources