loaditout.ai
SkillsPacksTrendingLeaderboardAPI DocsBlogSubmitRequestsCompareAgentsXPrivacyDisclaimer
{}loaditout.ai
Skills & MCPPacksBlog

prisma-review-tool

MCP Tool

Black-Lights/prisma-review-tool

Automated PRISMA 2020 systematic literature review with AI-assisted screening via MCP. Works with Claude, Codex, Copilot, Cursor, and any MCP-compatible agent.

Install

$ npx loaditout add Black-Lights/prisma-review-tool

Platform-specific configuration:

.claude/settings.json
{
  "mcpServers": {
    "prisma-review-tool": {
      "command": "npx",
      "args": [
        "-y",
        "prisma-review-tool"
      ]
    }
  }
}

Add the config above to .claude/settings.json under the mcpServers key.

About

PRISMA Review Tool

[](LICENSE)

Automated systematic literature review following the PRISMA 2020 guidelines (checklist | flow diagram | Page et al., 2021). Search academic databases, deduplicate results, screen papers with keyword rules, and use AI-assisted screening via any MCP-compatible agent — all from the command line.

Features
  • Multi-database search: arXiv, OpenAlex, Semantic Scholar (free, no API keys needed). Optional: Scopus.
  • Automatic deduplication: DOI matching + fuzzy title matching
  • Two-pass screening:
  • Pass 1: Rule-based keyword screening (automated)
  • Pass 2: AI-assisted eligibility screening via MCP (stricter criteria)
  • AI screening via MCP: Works with Claude Code, OpenAI Codex, GitHub Copilot, Cursor, Windsurf, Amazon Q, Gemini CLI, and any MCP-compatible agent
  • PRISMA flow diagram: Auto-generated PNG + Markdown with all the numbers
  • Export: BibTeX (.bib) for LaTeX/Zotero + CSV for Excel
  • PDF download: Automatically download open access papers (arXiv, Unpaywall, Semantic Scholar)
Quick Start
1. Setup
cd prisma_tool
python -m venv .venv

# Windows
.venv\Scripts\activate

# Mac/Linux
source .venv/bin/activate

pip install -r requirements.txt
2. Configure
cp config.template.yaml config.yaml

Edit config.yaml with your search queries, date range, and screening keywords. See docs/CONFIG_GUIDE.md for details.

3. Run
# Full pipeline
python -m prisma_review run-all

# Or step by step
python -m prisma_review search        # Search databases
python -m prisma_review dedup         # Remove duplicates
python -m prisma_review screen-rules  # Keyword screening
pyth

Tags

academic-researchai-screeningbibtexliterature-reviewmcpmodel-context-protocolprismaprisma-2020pythonsystematic-review

Reviews

Loading reviews...

Quality Signals

0
Installs
Last updated20 days ago
Security: AREADME

Safety

Risk Levelmedium
Data Access
read
Network Accessnone

Details

Sourcegithub-crawl
Last commit3/29/2026
View on GitHub→

Embed Badge

[![Loaditout](https://loaditout.ai/api/badge/Black-Lights/prisma-review-tool)](https://loaditout.ai/skills/Black-Lights/prisma-review-tool)