Bgpt Paper Search

This is an MCP server that searches scientific papers and returns structured experimental data extracted from full text, not just abstracts. You get 25+ fields per paper including methods, sample sizes, quantitative results, and quality scores. It's useful for lit reviews when you need the actual numbers and protocols buried in papers, or when building evidence tables for meta-analyses. Runs remotely via npx, no local install needed. Free tier gives you 50 searches per network, then it's a penny per result. The fact that it pulls from full-text extraction rather than just metadata makes it more useful than hitting PubMed, assuming the database covers your field.

skills.sh installs: 2.2K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill bgpt-paper-search --agent claude-code

Installs into .claude/skills of the current project.

Files

BGPT Paper Search

When to use

Use BGPT to find full-text-derived evidence for a research question or a known DOI. It returns extracted claims and their supporting experiments, rather than only bibliographic metadata. Use these records to build a traceable evidence table; they are not a complete systematic-review search or a validated risk-of-bias assessment.

Connect

Configure BGPT in the host before use; installing this skill does not register an MCP server. The provider supports both transports:

Transport	Endpoint
Streamable HTTP	`https://bgpt.pro/mcp/stream`
SSE	`https://bgpt.pro/mcp/sse`

Use the host's native remote-MCP configuration when supported. For a host that uses mcpServers JSON and requires a local stdio bridge, this configuration uses mcp-remote (adapt it to the host's actual settings format):

{
  "mcpServers": {
    "bgpt": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://bgpt.pro/mcp/stream", "--transport", "http-only"]
    }
  }
}

SKILL.md on GitHub