LitSynthLitSynth
  • Features
  • Pricing
  • FAQ
  • Literature Review
  • Blog

Loading…

LitSynthLitSynth

Transform your research workflow with AI-powered literature analysis and synthesis

DiscordEmail
Product
  • Features
  • Pricing
  • FAQ
Resources
  • Blog
  • Changelog
Friends
  • Find Papers
  • LitFigure – Scientific Figures
Company
  • Contact
Legal
  • Privacy Policy
  • Terms of Service

Research workflows

Explore focused guides for literature reviews, PubMed workflows, citation audits, and PRISMA-lite review planning.

AI literature review generatorsystematic review AI toolPRISMA litesystematic review screeningsystematic review data extractionsystematic review protocol generatorsemaglutide systematic review exampleAI in education literature review exampleclimate change health literature review example
©️ 2026 LitSynth. All Rights Reserved.

LITSYNTH / RELEASE NOTES

What changed.

A record of what shipped, why it matters, and where the evidence ends.

2026-09-09

v2026.09.09.3

Added

Generate saved reviews through authenticated MCP

Connect Codex to your account with scoped, expiring and revocable tokens.

  • Create tokens in Settings → Security; only a hash is stored and the secret is shown once.
  • Read your review runs, prepare selected papers and generate cited reviews through MCP.
  • Generation reuses workspace ownership, screening, preparation, plan, credit and duplicate-request gates.

Scope and limitations

Start the research question, search and confirm paper selection in the workspace. This release generates existing runs; it does not automate human inclusion decisions or certify review quality.

Configure authenticated MCP
2026-09-09

v2026.09.09.2

Added

Release notes and a public MCP interface

Inspect what changed and connect Codex to LitSynth’s public evidence and protocol checks.

  • Added a public changelog with dated, versioned release notes.
  • Added read-only MCP tools for release information, screening holdout results, paginated predictions, raw artifacts, and screening protocol validation.
  • Protocol validation reuses the application’s screening contract; it does not run AI screening or save a protocol.

Scope and limitations

This first MCP release does not access private projects, search for papers, generate reviews, or certify research quality. Authenticated research workflows are planned separately.

Connect Codex
2026-09-09

v2026.09.09.1

Improved

Clearer screening claims, complete benchmark context

Screening recommendations stay reviewable. Workload failures stay public.

  • Removed the promise that AI removes most repetitive reading; manual review savings vary by topic and corpus.
  • Updated the Rayyan comparison to acknowledge full-text screening, data extraction, and risk-of-bias workflows.
  • Published the benchmark at /systematic-review-screening-benchmark with auto-exclusion rate, protocol and policy versions, prediction timing, raw hashes, and explicit limitations.

Scope and limitations

The existing 281-record holdout was not rerun: zero false exclusions, 9/9 protected recall, 82.9% manual review, 15.7% auto exclusion. Workload gate FAIL; overall FAIL.

Inspect the benchmark