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

Related MCP server: MinerU Document Explorer

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

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}

• type parameter is integer (0-5), not string

• words is array of strings, not a single string

• question is required (despite docs saying optional)

• Paper search data field is a list, not {rows: [...]}

Environment Variables

License

Apache 2.0