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
Servidores relacionados
AgentBridge
A specialized gateway for AI agents to fetch and parse Chinese web content into clean Markdown. Pay-per-fetch via x402.
Library Docs MCP Server
Search and fetch documentation for popular libraries like Langchain, Llama-Index, and OpenAI using the Serper API, providing updated information for LLMs.
Wolfram Alpha
Access the Wolfram Alpha API for computational knowledge and real-time data.
Crawleo MCP Server
Crawleo MCP - Web Search & Crawl for AI Enable AI assistants to access real-time web data through native tool integration. Two Powerful Tools: web.search - Real-time web search with flexible formatting Search from any country/language Device-specific results (desktop, mobile, tablet) Multiple output formats: Enhanced HTML (AI-optimized, clean) Raw HTML (original source) Markdown (formatted text) Plain Text (pure content) Auto-crawl option for full content extraction Multi-page search support web.crawl - Deep content extraction Extract clean content from any URL JavaScript rendering support Markdown conversion Screenshot capture Multi-URL support Features: ✅ Zero data retention (complete privacy) ✅ Real-time, not cached results ✅ AI-optimized with Enhanced HTML mode ✅ Global coverage (any country/language) ✅ Device-specific search (mobile/desktop/tablet) ✅ Flexible output formats (4 options) ✅ Cost-effective (5-10x cheaper than competitors) ✅ Simple Claude Desktop integration Perfect for: Research, content analysis, data extraction, AI agents, RAG pipelines, multi-device testing
Tavily MCP Server
Web search using the Tavily API.
Typesense MCP Server
An MCP server for interacting with the Typesense search engine.
ThreatBook Threat Analysis
Provides threat intelligence queries for IPs, domains, files, URLs, and vulnerabilities using the ThreatBook API.
Google PSE/CSE
A Model Context Protocol (MCP) server providing access to Google Programmable Search Engine (PSE) and Custom Search Engine (CSE).
upfront rentals MCP
enables searching and booking car rentals
Weather MCP Server
Provides real-time weather forecasts and alerts using the National Weather Service API.