Bgpt Paper Search
Search full-text scientific papers and pull structured experimental fields through the BGPT MCP server for evidence-backed literature reviews.
Overview
BGPT Paper Search is an agent skill most often used in Idea (also Validate, Build) that queries the BGPT MCP server for scientific papers with 25+ full-text-derived structured fields per hit.
Install
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill bgpt-paper-searchWhat is this skill?
- Returns 25+ structured fields per paper (methods, results, sample sizes, quality scores, conclusions) beyond abstracts
- Connects via BGPT MCP (npx mcp-remote or npx bgpt-mcp) with optional API key for paid usage
- Supports literature reviews, evidence synthesis, and cross-study methodology comparison
- Targets experimental details such as effect sizes and grading not visible in title/abstract-only search
- 25+ metadata fields per paper returned from full-text extraction
Adoption & trust: 595 installs on skills.sh; 27.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need experimental methods, sample sizes, and graded evidence from papers but abstract-only search and manual PDF triage do not scale in the agent loop.
Who is it for?
Indie builders doing literature reviews, health/science features, or competitive technical diligence that needs quantitative study fields in the agent context.
Skip if: Builders who only need casual blog links, have no MCP host setup, or cannot use network-backed third-party research APIs.
When should I use this skill?
Searching for scientific papers with specific experimental details, conducting systematic or scoping literature reviews, or needing quantitative results and quality scores not available in abstracts alone.
What do I get? / Deliverables
You get structured paper records your agent can rank, compare, and cite in reviews or specs without re-parsing PDFs by hand.
- Structured paper result sets with methods, results, and quality metadata
- Agent-ready evidence for synthesis or comparison tables
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Idea because the primary job is discovery and synthesis of published evidence before product or technical commitments. Research subphase matches systematic and scoping reviews, methodology comparison, and quantitative extraction from studies rather than building features.
Where it fits
Compare RCT methodologies before choosing a health-feature narrative for your landing page.
Pull sample sizes and conclusions across studies to decide whether a claim is defensible in an MVP spec.
Populate internal docs or agent context with graded evidence tables sourced from BGPT fields.
How it compares
Structured full-text experimental fields via MCP—not the same as dropping a generic web-search or PubMed abstract snippet into chat.
Common Questions / FAQ
Who is bgpt-paper-search for?
Solo builders and agent users who synthesize scientific evidence, compare study methods, or need citable quantitative details during research-heavy product or docs work.
When should I use bgpt-paper-search?
Use it in Idea research for scoping reviews, in Validate when proving claims with published data, and in Build docs when embedding methods, sample sizes, or quality scores from primary studies.
Is bgpt-paper-search safe to install?
It depends on your threat model for remote MCP and API usage; review the Security Audits panel on this Prism page and your BGPT API key handling before enabling network tools in production agents.
SKILL.md
READMESKILL.md - Bgpt Paper Search
# 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: ```json { "mcpServers": { "bgpt": { "command": "npx", "args": ["mcp-remote", "https://bgpt.pro/mcp/sse"] } } } ``` ### npm (alternative) ```bash 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](https://bgpt.pro/mcp)