About PubMed MCP Server
PubMed MCP Server provides access to PubMed for users and applications that need biomedical literature. It supports article search, detailed metadata retrieval, and downloading PMC article PDFs locally.
Key features
- 01Search PubMed articles
- 02Retrieve article metadata
- 03Download PMC article PDFs
Use cases
- 01Finding papers by keyword
- 02Reviewing article abstracts and authors
- 03Saving PMC PDFs locally
MCP support
The server exposes PubMed search, metadata retrieval, and PMC PDF download capabilities to MCP clients over an SSE endpoint.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPubMed MCP Server
项目简介
PubMed MCP Server 是一个基于 fastapi-mcp 的服务,提供了对 PubMed 数据库的访问接口。该服务允许用户搜索 PubMed 文章、获取文章元数据以及下载 PMC 文章的 PDF 文件
基本功能:
- 搜索文章:根据关键词搜索 PubMed 数据库中的文章
- 获取元数据:获取特定 PubMed ID 的文章详细信息,包括标题、摘要、作者、关键词等
- 下载 PDF:下载 PMC 文章的 PDF 文件到本地
安装与配置
- 克隆仓库
git clone https://github.com/yourusername/pubmed-mcp-server.git
cd pubmed-mcp-server
# 安装 uv 工具,用于管理虚拟环境和依赖项同步
pip install uv
- 创建并激活虚拟环境
uv sync
source .venv/bin/activate # Linux/Mac
# 或
.venv\Scripts\activate # Windows
配置
创建 .env 文件来自定义配置:
DOWNLOAD_PATH=/path/to/store/pdfs
默认情况下,PDF 文件将保存在 /tmp/pubmed-pdfs 目录下。
使用方法
uv run main.py
服务器将在 http://localhost:8977 上运行。
然后你可以在 mcp client 中配置这个endpoint,并使用SSE模式
项目结构
.
├── app/ # API 应用定义
│ └── pubmed.py # PubMed API 端点
├── core/ # 核心功能
│ └── config.py # 配置管理
├── service/ # 服务层
│ ├── __init__.py # 基础 URL 和工具函数
│ ├── file.py # 文件下载功能
│ └── search.py # PubMed 搜索和解析功能
├── tests/ # 测试目录
├── .env # 环境变量配置
├── main.py # 应用入口
└── pyproject.toml # 项目依赖
许可证
本项目采用 MIT 许可证。详情请参阅 LICENSE 文件。
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.