bgpt-paper-search
k-dense-ai/scientific-agent-skills
Search scientific papers and extract structured experimental data from full-text studies via BGPT MCP server.
What is bgpt-paper-search?
BGPT Paper Search retrieves detailed experimental metadata from scientific papers—methods, results, sample sizes, quality scores, and 25+ fields per paper—rather than just abstracts. Use it for literature reviews, evidence synthesis, meta-analyses, and finding quantitative details across multiple studies.
- Search a curated database of scientific papers with full-text experimental data extraction
- Retrieve 25+ structured fields per paper including methods, results, sample sizes, and quality assessments
- Compare methodologies and quantitative findings across studies
- Access evidence grading and study quality scores
- Build structured data tables for systematic reviews and meta-analyses
- Find experimental details not available in abstract-only databases
How to install bgpt-paper-search
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill bgpt-paper-search- BGPT MCP server configured in agent host (via npx mcp-remote or npx bgpt-mcp)
- Internet access to bgpt.pro
- Optional: BGPT API key from bgpt.pro/mcp for paid usage beyond free tier (50 searches per network)
How to use bgpt-paper-search
- 1.Configure BGPT MCP server in your agent's MCP settings using the provided JSON configuration or npm command
- 2.Ensure the MCP server is running and accessible
- 3.Call the search_papers MCP tool via your agent interface with a query about specific experimental details or paper topics
- 4.Review the structured results including methods, quantitative findings, sample sizes, and quality scores
- 5.Export or organize the returned data fields for your literature review, evidence table, or meta-analysis
Use cases
- Conducting systematic or scoping literature reviews with quantitative data requirements
- Extracting sample sizes and effect sizes for meta-analysis preparation
- Comparing experimental methodologies across multiple studies in a research domain
- Building evidence tables for clinical guidelines or policy recommendations
- Finding papers with specific quality thresholds or evidence grades for evidence synthesis
- Researchers conducting literature reviews or meta-analyses
- Evidence synthesis specialists and systematic review authors
- Clinical guideline developers
- Academic researchers in biomedical and life sciences
- Data analysts building evidence databases
bgpt-paper-search FAQ
BGPT extracts and structures data from full-text papers (methods, results, sample sizes, quality scores), whereas traditional databases return only titles and abstracts. This enables direct access to quantitative findings and experimental details.
No. The free tier provides 50 searches per network without an API key. Paid usage ($0.01 per result) requires an API key from bgpt.pro/mcp.
BGPT returns 25+ fields including title, authors, journal, year, DOI, experimental methods, quantitative results, sample sizes, quality assessments, and author conclusions.
Yes. BGPT's structured extraction of sample sizes, effect sizes, and methodologies is designed to support meta-analysis and evidence table construction.
Yes. BGPT is a remote MCP server that must be configured in your agent's MCP settings (via npx mcp-remote or npx bgpt-mcp) before the skill can access the search_papers tool.
Full instructions (SKILL.md)
Source of truth, from k-dense-ai/scientific-agent-skills.
name: bgpt-paper-search description: Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone. license: MIT compatibility: Requires the BGPT MCP server configured in the agent host (npx mcp-remote or npx bgpt-mcp), internet access to bgpt.pro, and an optional BGPT API key for paid usage. metadata: version: "1.1" skill-author: BGPT website: https://bgpt.pro/mcp github: https://github.com/connerlambden/bgpt-mcp
BGPT 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. Configure it in your agent's MCP settings before use; this skill instructs the agent to call the search_papers MCP tool and does not enable MCP access by itself.
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 the BGPT MCP server is configured, call its search_papers tool via the agent's MCP interface (not via Bash):
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
Related skills
More from k-dense-ai/scientific-agent-skills and the wider catalog.
bids
Organize and query neuroscience datasets using the Brain Imaging Data Structure (BIDS) standard.
biopython
Comprehensive Python toolkit for sequence manipulation, file parsing, and NCBI database access in bioinformatics workflows.
bioservices
Unified Python interface to 40+ bioinformatics databases for cross-database queries and ID mapping.
cellxgene-census
Query 217M+ cells from CZ CELLxGENE Census for single-cell and spatial transcriptomics data without downloading whole datasets.
cirq
Google's quantum computing framework for designing and running circuits on quantum hardware and simulators.
citation-management
Search academic databases, extract metadata, and generate properly formatted BibTeX citations for research.