BGPT MCP API

Keep your AI closer to the latest evidence.

Build scientific AI that can show its work.

Search by topic or DOI. Retrieve claims linked to experiments, exact results, scope, limitations, falsification criteria, and source provenance.

When an answer matters, you can trace it back to what each paper actually showed.

Check the answerSee the experiments and exact results behind each claim.

Trace it to the sourceFollow evidence to source sections, figures, tables, and text.

See where it stopsKeep scope, biases, extraction status, and uncertainty visible.

Built forscientific model training · literature review · RAG · research agents

Pick your tool, copy the config, and start searching.

Add to~/.claude/claude_desktop_config.json:

{ "mcpServers": { "bgpt": { "url": "https://bgpt.pro/mcp/sse" } } }

Add to.cursor/mcp.jsonin your project root:

{ "mcpServers": { "bgpt": { "url": "https://bgpt.pro/mcp/sse" } } }

claude mcp add bgpt --transport sse https://bgpt.pro/mcp/sse

Traditional HTTP API. No key needed for the first 50 results.

import requests def search_bgpt(query, num_results=16, days_back=None, api_key=None, output_format="evidence"): payload = { "query": query, "num_results": num_results, "output_format": output_format, } if days_back is not None: payload["days_back"] = days_back if api_key: payload["api_key"] = api_key response = requests.post( "https://bgpt.pro/api/mcp-search", json=payload, timeout=60, ) response.raise_for_status() return response.json()["results"] papers = search_bgpt("CRISPR delivery neurons", num_results=5) paper = papers[0] print(paper["central_claim"]) if paper["evidence"]["evidence_units"]: unit = paper["evidence"]["evidence_units"][0] print(unit["claim"]) print(unit.get("result", {}).get("reported_statistics", [])) print(unit["provenance"])

Endpoints for any MCP-compatible client:

Endpoints: SSE: https://bgpt.pro/mcp/sse Streamable HTTP: https://bgpt.pro/mcp/stream Tools: search_papers query (required) Search terms num_results (optional) 1-100, default 16 days_back (optional) Filter to recent papers output_format(optional) evidence, full, or legacy lookup_paper doi (required) DOI of the paper output_format(optional) evidence, full, or legacy

- Add the configabove to your AI tool
- Ask your AIto search, e.g.“Search BGPT for CRISPR delivery methods in neurons”or look up a specific paper by DOI
- Get evidence unitslinking claims to experiments, results, scope, and provenance

Your first 50 results are free. After that, add billing at $0.02/result.

One result is one structured paper record.

- ✓ 50 free results
- ✓ Evidence ready for training and RAG
- ✓ No API key needed

- ✓ Unlimited searches
- ✓ Evidence ready for training and RAG
- ✓ Pay only for returned results

Useoutput_format="evidence"for compact records or"full"to add legacy metadata.

Search responses place records inresults. DOI lookup places the record inresultand includesfound. Evidence and full output omit papers without extracted evidence.

evidence.schema_versionandextraction_status

evidence.evidence_units: claims linked to experiments

claim_type: causal, correlational, mechanistic, descriptive, diagnostic, prognostic, efficacy, or safety

evidence_status: supported, mixed, contradicted, or not_assessable

evidence_basis: direct, indirect, or synthesized

relation_to_central_claim: supports, qualifies, challenges, or independent

experiment: design, independent units, groups, outcomes, and methods

reported_statistics: exact reported value text, comparison, test, and analysis model

applicability.demonstrated_in: demonstrated scope

provenance[]: section, figure, table, exact source text

evidence.record_provenance: source hash, extraction time, truncation status

counterevidence_or_ambiguity[]: reported or inferred qualifiers

limitations[]: reported or inferred limits

evidence_units[].falsification_criteria[]: concrete weakening tests with basis

how_to_falsify: concise paper-level criterion

implicit_assumptions: useful tacit knowledge the paper leans on but never states

limitations_and_biases: concise paper-level synthesis

sample_size_and_population_characteristics

legacy metadata: retained for existing clients

Coverage reflects the available full text and what the paper reports. Empty optional fields are omitted from compact evidence output. V4 records contain at most 5 evidence units and 2 provenance passages per unit; each passage is at most 320 characters. Older records retain their explicit schema version.extraction_statusand anynormalization_warningsexpose incomplete or repaired records.

Just add the config above to your AI tool and start asking questions. No sign-up, no API key needed. You get50 free resultsautomatically.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

Provides comprehensive patent search and statistical analysis for intelligence analysis, technological innovation, and intellectual property management.

Provides MCP tools to search, download, and manage 1M+ research records (papers, images, videos, datasets) from the Compoid AI content repository

Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.

Search for scientific publications across ArXiv, ACL Anthology, HuggingFace Datasets, and Semantic Scholar.

Research papers from arXiv, Google Scholar, and Wikipedia with citation metrics

An MCP (Model Context Protocol) server for searching and analyzing academic papers across multiple databases (Semantic Scholar, Crossref, OpenAlex, PubMed), with regex-powered filtering and statistical analysis.

A flexible service for searching and analyzing academic papers on arXiv.

Live Austin-area MLS listings in your AI assistant — active listings, property details, schools, taxes, and neighborhood data for the Austin metro. Free remote MCP server, no install.

Search scientific papers with structured experimental data extracted from full-text studies. Returns 25+ fields per paper including methods, results, sample sizes, limitations, and quality scores.

A server for Retrieval-Augmented Generation (RAG) using the Contextual AI platform.