PubMed Search MCP Server

by YOUNGSUK81

80 downloads

Not rated

GitHub

About

MCP server for PubMed medical research search with Impact Factor analysis

Details

Author: YOUNGSUK81
Downloads: 80
Categories: Search

- Analyzes medical questions and searches PubMed for relevant articles
- Filters results by relevance using title, abstract, and MeSH terms
- Sorts articles by journal Impact Factor for influential research
- Outputs EndNote-compatible format for literature management
- Provides three categorized result files: relevance, impact factor, and unknown
- Supports pubmed_search and load_impact_factor MCP tools

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name PubMed Search MCP Server

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

From the repository

Install Node.js 16+, obtain a free NCBI API key, and prepare an Impact Factor data JSON file. Clone the repository, run npm install and npm run build, set environment variables (NCBI_API_KEY, IMPACT_FACTOR_PATH, OUTPUT_DIR), then configure the server in your MCP client (e.g., Claude Desktop, VS Code).

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "pubmed search mcp server": {
            "Pubmed_Search": {
                "command": "node",
                "args": [
                    "impact-factor-converter.js",
                    "impact-factor.pdf",
                    "impact_factor_data.json"
                ]
            }
        }
    }
}

McpServers

{
    "Pubmed_Search": {
        "command": "node",
        "args": [
            "impact-factor-converter.js",
            "impact-factor.pdf",
            "impact_factor_data.json"
        ]
    }
}

PubMed Search MCP Server

Model Context Protocol(MCP) 서버로, 의학 주제에 관한 질문을 분석하여 PubMed에서 관련 논문을 검색하고 연관성 및 저널 Impact Factor에 따라 결과를 EndNote 형식으로 제공합니다.

주요 기능

- 검색 쿼리 분석: 의학 관련 질문을 분석하여, PubMed API를 통해 의학 논문 검색
- 연관성 분석: 논문의 제목, 초록, MeSH 용어 등을 분석하여 질문과 가장 관련성 높은 논문 선별
- Impact Factor 기반 정렬: 저널의 Impact Factor에 따라 논문을 정렬하여 영향력 높은 연구 제공
- EndNote 형식 출력: 선별된 논문을 EndNote 호환 포맷으로 출력하여 문헌 관리 용이
- 결과 분류: 세 가지 파일로 결과 제공
- 연관성이 높은 논문 목록
- Impact Factor가 높은 논문 목록
- Impact Factor 데이터베이스에 없는 저널의 논문 목록

도구 설명

- pubmed_search: PubMed에서 의학 논문 검색 및 분석
- 입력:
- query (string, 필수): 의학 관련 질문 또는 검색 쿼리
- maxResults (number, 선택, 기본값: 10): 반환할 최대 결과 수
- outputDir (string, 선택, 기본값: "./output"): 결과 파일을 저장할 디렉터리 경로

- load_impact_factor: Impact Factor 데이터 파일 로드
- 입력:
- filePath (string, 필수): Impact Factor 데이터 파일 경로

설치 및 설정

필수 조건

- Node.js 16 이상
- NCBI API 키 (무료로 발급 가능: https://ncbiinsights.ncbi.nlm.nih.gov/2017/11/02/new-api-keys-for-the-e-utilities/)
- Impact Factor 데이터 JSON 파일

Impact Factor 데이터 변환

PDF 형식의 Impact Factor 데이터를 JSON으로 변환:

```bash

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

PubMed Search MCP Server

주요 기능

도구 설명

설치 및 설정

필수 조건

Impact Factor 데이터 변환

Install

More like this

Brave Search

🔎 GPT Researcher

Github SSE

AWS MCP Servers

Yoyo

whatsapp-mcp