Who it is for
Anyone checking whether a scientific claim has held up, from clinicians to science journalists.
Overview
Scite answers research questions from peer-reviewed literature and returns the sources behind each response. What separates its output from a plain reference list is the treatment of how a cited study has been received: whether later work supported it, disputed it, or mentioned it in passing.
Ranking is done by a citation-based model built by the company, which orders results by how well a finding has held up in subsequent literature.
The practical effect is that a reader sees the claim, the source, and the state of the argument around it.
Anyone checking whether a scientific claim has held up, from clinicians to science journalists.
Citations arrive with an indication of whether later studies backed or contested the finding, not just a reference string.
Availability
Scite ships this on both marketplaces: Scite is listed in the Claude connectors directory and in the ChatGPT apps directory, under the same publisher domain.
Only 392 of the 3,150 products in this directory are listed in both marketplaces. One MCP server can serve both surfaces; what differs is each platform's listing and review process.
ChatGPT listing
Claude listing
Scite publishes 1 tool to Claude, a deliberately narrow surface; only 0.7% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Healthcare & Life Sciences publishes 6, so this one sits 5 tools below its bucket's median, 49th of 51.
It falls in the 1-3 tools band, which holds 16.4% of the Claude directory.
A direct call to the endpoint returned 25 tools, 24 more than the 1 the listing publishes. Probed 2026-08-07.
search_literaturesearch_patentssearch_clinical_trialsget_clinical_trialsearch_grantsget_grantsearch_device510kget_device510ksearch_510k_summariesget_510k_summarysearch_mhraget_mhra_alertsearch_maudeget_maude_reportsearch_faersget_faers_reportsearch_drugsget_drugcreate_collectionget_collectionsearch_collectionsupdate_collectiondelete_collectionadd_dois_to_collectionremove_dois_from_collectionScite publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
https://api.scite.ai/mcp Scite carries partner verification in the Claude directory, which 474 of 1,253 listings do (37.8%). That is a review step past self-publishing, not an Anthropic-built server.
In the publisher's words
Scite delivers answers grounded in peer-reviewed research you can verify. Each response is backed by real scientific sources, with citations that show how studies have been supported, disputed, or contextualized by other researchers. Behind the scenes, Scite’s proprietary citation-based ranking model prioritizes trustworthy, validated research, helping users move beyond claims to evidence.
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
Benchling research data through its own scientific AI chat
Claude
Agentic life science literature reviews returned as cited briefs
Claude
Search US providers and health systems by claims volume
Claude
Antimicrobial peptide design and vaccine target scoring with EDEN
Claude
Function Health lab panels, answers and nutrition guidance
Claude
Short guided mental health exercises inside ChatGPT
ChatGPT
This is an independent catalogue entry compiled by Node8 from Scite's public marketplace listings as they stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with Scite, and inclusion here is not an endorsement.
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.