[GH-ISSUE #844] Add BGPT API as a scientific RAG / research-agent example #6488

Open
opened 2026-05-31 13:51:08 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @connerlambden on GitHub (May 26, 2026).
Original GitHub issue: https://github.com/Shubhamsaboo/awesome-llm-apps/issues/844

Hi, I'd like to suggest BGPT API as a scientific retrieval source for scientific RAG and LLM-agent apps.

BGPT is a REST/Python API and MCP server for searching scientific papers. Unlike a generic web or abstract search tool, it returns structured evidence extracted from full-text studies: methods, results, sample sizes/populations, study context, limitations, conflicts of interest, data/code availability, quality scores, and fields for falsifiability / study blindspots.

Links:

Why it fits:

  • It gives RAG and agent systems structured scientific evidence rather than unstructured snippets.
  • The API is easy to call from Python notebooks, Postman, OpenAPI clients, or MCP-compatible agents.
  • It is useful for scientific QA, literature review, claim checking, and evidence dashboards.

Possible listing:

BGPT API - REST/Python and MCP retrieval source for scientific papers, returning structured full-text evidence fields for research-focused RAG and agents.

Originally created by @connerlambden on GitHub (May 26, 2026). Original GitHub issue: https://github.com/Shubhamsaboo/awesome-llm-apps/issues/844 Hi, I'd like to suggest BGPT API as a scientific retrieval source for scientific RAG and LLM-agent apps. BGPT is a REST/Python API and MCP server for searching scientific papers. Unlike a generic web or abstract search tool, it returns structured evidence extracted from full-text studies: methods, results, sample sizes/populations, study context, limitations, conflicts of interest, data/code availability, quality scores, and fields for falsifiability / study blindspots. Links: - Docs: https://bgpt.pro/mcp/ - GitHub: https://github.com/connerlambden/bgpt-mcp - REST endpoint: `POST https://bgpt.pro/api/mcp-search` - OpenAPI: https://raw.githubusercontent.com/connerlambden/bgpt-mcp/main/openapi.yaml - Postman collection: https://raw.githubusercontent.com/connerlambden/bgpt-mcp/main/examples/postman_collection.json - Python example: https://github.com/connerlambden/bgpt-mcp/blob/main/examples/bgpt_rest_python.py Why it fits: - It gives RAG and agent systems structured scientific evidence rather than unstructured snippets. - The API is easy to call from Python notebooks, Postman, OpenAPI clients, or MCP-compatible agents. - It is useful for scientific QA, literature review, claim checking, and evidence dashboards. Possible listing: `BGPT API - REST/Python and MCP retrieval source for scientific papers, returning structured full-text evidence fields for research-focused RAG and agents.`
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/awesome-llm-apps#6488