Home
cd ../playbooks
Research & WritingBeginner

Scientific Bgpt Paper Search

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...

5 minutes
By K-Dense AISource
#scientific#claude-code#bgpt-paper-search#visualization#database#protein#genomics#writing

PubMed gives you abstracts, but the methods, results, and sample sizes you actually need are buried in the full text. BGPT extracts structured experimental data from papers — 25+ fields including methods, results, quality scores, and conclusions — so you can search the literature by what was actually found, not just what was claimed in the abstract.

Who it's for: researchers conducting systematic literature reviews with structured data extraction, graduate students building evidence tables for thesis chapters, meta-analysis teams collecting quantitative results across studies, scientific writers verifying experimental details from primary sources, lab PIs staying current with structured paper summaries in their field

Example

"Search for papers on CRISPR efficiency in T-cells with structured experimental data" → Structured results: papers ranked by relevance with extracted methods (cell type, guide RNA design), quantitative results (editing efficiency percentages), sample sizes, quality scores, experimental conditions, and a comparison table across studies

CLAUDE.md Template

New here? 3-minute setup guide → | Already set up? Copy the template below.

# 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.

### Claude Desktop / Claude Code

Add to your MCP configuration:

```json
{
  "mcpServers": {
    "bgpt": {
      "command": "npx",
      "args": ["mcp-remote", "https://bgpt.pro/mcp/sse"]
    }
  }
}
```

### npm (alternative)

```bash
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](https://bgpt.pro/mcp)

## Complementary Workflows

Pairs well with:
- `literature-review` — Use BGPT to gather structured data, then synthesize with literature-review workflows
- `pubmed-database` — Use PubMed for broad searches, BGPT for deep experimental data
- `biorxiv-database` — Combine preprint discovery with full-text data extraction
- `citation-management` — Manage citations from BGPT search results
README.md

What This Does

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.


Quick Start

Step 1: Create a Project Folder

mkdir -p ~/Projects/bgpt-paper-search

Step 2: Download the Template

Click Download above, then:

mv ~/Downloads/CLAUDE.md ~/Projects/bgpt-paper-search/

Step 3: Start Claude Code

cd ~/Projects/bgpt-paper-search
claude

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 Workflows

Pairs well with:

  • literature-review — Use BGPT to gather structured data, then synthesize with literature-review workflows
  • pubmed-database — Use PubMed for broad searches, BGPT for deep experimental data
  • biorxiv-database — Combine preprint discovery with full-text data extraction
  • citation-management — Manage citations from BGPT search results

Tips

  • Read the docs: Check the official bgpt-paper-search documentation for latest API changes
  • Start simple: Begin with basic examples before tackling complex workflows
  • Save your work: Keep intermediate results in case of long-running analyses

$Related Playbooks