BGPT MCP API
Search scientific papers from any MCP tool. Raw experimental data from full-text papers — methods, results, quality scores. 50 free searches, then $0.01/result.
BGPT
MCP: Search Daily-Updated Scientific Data
Add BGPT to Claude, Cursor, or any MCP tool.
We extract raw experimental results from full-text papers—the actual data, methods, and findings—so your AI gets answers grounded in evidence, not summaries.
50 free results · Then $0.02/result
Start Searching
Get Started in 30 Seconds
Pick your tool, copy the config, and start searching.
Claude Desktop
Cursor
Claude Code
Other
Add to ~/.claude/claude_desktop_config.json:
{ "mcpServers": { "bgpt": { "url": "https://bgpt.pro/mcp/sse" } } }
Copy Config
Add to .cursor/mcp.json in your project root:
Copy Config
Run in your terminal:
claude mcp add bgpt --transport sse https://bgpt.pro/mcp/sse
Copy Command
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 10 days_back (optional) Filter to recent papers
lookup_paper doi (required) DOI of the paper
Copy
How It Works
- Add the config above to your AI tool
- Ask your AI to search, e.g. “Search BGPT for CRISPR delivery methods in neurons” or look up a specific paper by DOI
- Get results with full metadata from real experimental data
Your first 50 results are free. After that, subscribe below for unlimited access at $0.02/result.
Pricing
Free Tier
$0
- ✓ 50 free results
- ✓ All paper metadata fields
- ✓ No API key needed
Pay-as-you-go
$0.02 / result
- ✓ Unlimited searches
- ✓ All paper metadata fields
- ✓ Metered Stripe billing Subscribe →
What You Get Per Paper
Every result includes 25+ fields extracted from the full text of published studies.
Identification
doi — DOI identifier
title — Paper title
publication_date
publication_name — Journal
Content & Analysis
one_sentence_summary
keywords
results_and_conclusions
methods_and_experimental_techniques
sample_size_and_population
list_of_extracted_data
problem_statement
study_context
Critical Evaluation
how_to_falsify
study_blindspots
paper_limitations_and_biases
conflict_of_interest
Technical Details
taxonomy_information
experimental_models
software_and_tools_used
data_availability_statements
code_and_data_links
lab_name
Citations & Quality
funding_json
citations_json
reference_count
Quality scores — scientific, novelty, generality, usefulness, reproducibility, depth
Frequently Asked Questions
How do I start searching for free?
Just add the config above to your AI tool and start asking questions. No sign-up, no API key needed. You get 50 free results automatically.
What happens when I use up my 50 free results?
How do I subscribe and get my API key?
How do I use my API key?
How does billing work exactly?
What does days_back do?
Where do I find my API key if I lost it?
Can I cancel anytime?
Need help?
Back to BGPT
相关服务器
Search MCP Server
A versatile search server supporting multiple search engines, including Brave, Metaso, and Bocha.
Perplexity
Web search using the Perplexity API with automatic model selection based on query intent.
Rememberizer Common Knowledge
Provides semantic search and retrieval for internal company knowledge bases, including documents and Slack discussions.
mcp-domain-radar
MCP server that checks domain availability in real-time during brand naming — never recommend a name without a domain again
workx.am Armenia Jobs
Search jobs, companies, candidates, and salaries from Armenia's #1 job platform - 12 tools, no auth required.
USGS Quakes
Access earthquake data from the USGS Quakes API using natural language queries.
SearchAPI Agent
An MCP agent that integrates various search tools using the SearchAPI service. Requires SearchAPI and Google API keys.
PubMed Search
Search for biomedical literature from the PubMed database.
Amazon Product Search
An AI-powered server for Amazon product search and recommendations.
Academic Paper Search
Search and retrieve academic paper information from multiple sources like Semantic Scholar and CrossRef.