Bohrium MCP Server
Enables searching academic papers and patents, parsing PDFs, and managing knowledge bases via Bohrium Open Platform through any MCP-compatible AI agent.
README
Bohrium MCP Server
MCP server for Bohrium Open Platform — search academic papers, patents, parse PDFs, and manage knowledge bases through any MCP-compatible AI agent.
Features
- Paper Search: Search English academic papers with keyword + semantic question matching
- Patent Search: Search global patents with assignee and date filters
- PDF Parsing: Submit PDFs for structured extraction (async with polling)
- Knowledge Base: Create, list, and search within curated knowledge bases
Quick Start
1. Get API Key
Visit https://bohrium.dp.tech/settings/user to generate your access key.
2. Install
pip install "mcp>=1.0.0" "httpx>=0.27.0" "pydantic>=2.0.0"
3. Run
ACCESS_KEY=your_key_here python server.py
4. Configure with Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"bohrium": {
"command": "python",
"args": ["/path/to/bohrium_mcp_server/server.py"],
"env": {
"ACCESS_KEY": "your_bohrium_api_key"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
bohrium_search_papers |
Search academic papers by keywords + research question |
bohrium_search_patents |
Search global patents by keywords + question |
bohrium_parse_pdf_by_url |
Submit a PDF URL for structured parsing |
bohrium_parse_pdf_by_file |
Submit a local PDF file for parsing |
bohrium_get_pdf_parse_result |
Poll for PDF parsing result |
bohrium_list_knowledge_bases |
List all knowledge bases |
bohrium_create_knowledge_base |
Create a new knowledge base |
bohrium_search_kb_file_content |
Search within a knowledge base |
Paper Search Example
# The agent calls:
bohrium_search_papers(
words=["EGFR", "inhibitor", "lung cancer"],
question="What are the latest EGFR targeted therapies for NSCLC?",
search_type=0, # 0=fast keyword, 1-4=enhanced with ranking
page_size=10,
area_ids=["11"], # 11=Medicine
)
Returns formatted results with title, DOI, journal, date, and citation count.
API Notes
- Base URL:
https://openapi.dp.tech/openapi/v1 - Auth: Header
accessKey: {your_key} typeparameter is integer (0-5), not stringwordsis array of strings, not a single stringquestionis required (despite docs saying optional)- Paper search
datafield is a list, not{rows: [...]}
Environment Variables
| Variable | Required | Description |
|---|---|---|
ACCESS_KEY |
Yes (or BOHRIUM_API_KEY) |
Bohrium platform API key |
License
Apache 2.0
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.