bgpt-paper-search
Scannednpx machina-cli add skill K-Dense-AI/claude-scientific-skills/bgpt-paper-search --openclawBGPT Paper Search
Overview
BGPT is a remote MCP server that searches a curated database of scientific papers built from raw experimental data extracted from full-text studies. Unlike traditional literature databases that return titles and abstracts, BGPT returns structured data from the actual paper content — methods, quantitative results, sample sizes, quality assessments, and 25+ metadata fields per paper.
When to Use This Skill
Use this skill when:
- Searching for scientific papers with specific experimental details
- Conducting systematic or scoping literature reviews
- Finding quantitative results, sample sizes, or effect sizes across studies
- Comparing methodologies used in different studies
- Looking for papers with quality scores or evidence grading
- Needing structured data from full-text papers (not just abstracts)
- Building evidence tables for meta-analyses or clinical guidelines
Setup
BGPT is a remote MCP server — no local installation required.
Claude Desktop / Claude Code
Add to your MCP configuration:
{
"mcpServers": {
"bgpt": {
"command": "npx",
"args": ["mcp-remote", "https://bgpt.pro/mcp/sse"]
}
}
}
npm (alternative)
npx bgpt-mcp
Usage
Once configured, use the search_papers tool provided by the BGPT MCP server:
Search for papers about: "CRISPR gene editing efficiency in human cells"
The server returns structured results including:
- Title, authors, journal, year, DOI
- Methods: Experimental techniques, models, protocols
- Results: Key findings with quantitative data
- Sample sizes: Number of subjects/samples
- Quality scores: Study quality assessments
- Conclusions: Author conclusions and implications
Pricing
- Free tier: 50 searches per network, no API key required
- Paid: $0.01 per result with an API key from bgpt.pro/mcp
Complementary Skills
Pairs well with:
literature-review— Use BGPT to gather structured data, then synthesize with literature-review workflowspubmed-database— Use PubMed for broad searches, BGPT for deep experimental databiorxiv-database— Combine preprint discovery with full-text data extractioncitation-management— Manage citations from BGPT search results
Source
git clone https://github.com/K-Dense-AI/claude-scientific-skills/blob/main/scientific-skills/bgpt-paper-search/SKILL.mdView on GitHub Overview
BGPT Paper Search uses a remote MCP server to extract structured data directly from full-text studies. It returns 25+ fields per paper, including methods, quantitative results, sample sizes, quality scores, and conclusions. This enables rigorous literature reviews, evidence synthesis, and discovery of experimental details not available in abstracts.
How This Skill Works
Configure BGPT MCP as a remote server and issue a search_papers query. The server parses full-text content and returns structured records with experimental methods, quantitative results, sample sizes, and quality assessments. Use the results to assemble comprehensive evidence tables for meta-analyses or guidelines.
When to Use It
- Looking for papers with specific experimental details (methods, protocols, models)
- Conducting systematic or scoping literature reviews
- Finding quantitative results, sample sizes, or effect sizes across studies
- Comparing methodologies across papers or laboratories
- Building evidence tables for meta-analyses or clinical guidelines
Quick Start
- Step 1: Add BGPT MCP as a remote server (mcpServers) to your configuration
- Step 2: Run a search_papers query with your topic, e.g. 'CRISPR efficiency in human cells'
- Step 3: Parse the structured results to build tables of methods, results, and quality scores
Best Practices
- Define precise search terms for the targeted experimental details
- Ensure full-text access to extract data beyond abstracts
- Cross-check units, sample sizes, and data consistency across papers
- Record quality scores or evidence grading where provided
- Combine BGPT results with traditional databases for thorough synthesis
Example Use Cases
- CRISPR gene editing efficiency in human cells with full experimental details
- Dose–response relationships for a cancer drug across multiple trials
- Protein expression levels across different cell lines with sample sizes
- Surgical technique outcomes with procedural methods and results
- Quality scores and conclusions for prognostic biomarker studies
