広告掲載
MCP.so
ログイン

PubMed Enhanced Search Server MCP Server

@leescot

リポジトリ

基本情報

カテゴリ

データと分析

トランスポート

stdio

作者

leescot

投稿者

坤峰 李

PubMed Enhanced Search Server MCP Server について

pubmed-mcp-smithery

#pubmed#mcp#academic-research

PubMed Enhanced Search Server MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "pubmed-mcp-smithery": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "@leescot/pubmed-mcp-smithery",
        "--config",
        "\"{}\""
      ]
    }
  }
}

PubMed Enhanced Search Server MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is PubMed Enhanced Search Server?

A Model Context Protocol (MCP) server that provides tools to search and retrieve academic papers from the PubMed database. It includes enhanced features such as MeSH term lookup, publication count statistics, and PICO-based evidence search. Designed for researchers, clinicians, and anyone conducting medical literature reviews.

How to use PubMed Enhanced Search Server?

Install Python 3.6+, fastmcp, and requests; then clone the repository and start the server with python pubmed_enhanced_mcp_server.py or in development mode with mcp dev pubmed_enhanced_mcp_server.py. Add the server to Claude Desktop by editing the claude_desktop_config.json file with the server's command and path.

Key features of PubMed Enhanced Search Server

  • Search PubMed by keywords with optional journal filter
  • Sort results by relevance or date (newest/oldest)
  • Look up MeSH terms related to a medical concept
  • Get publication counts for multiple search terms
  • Retrieve detailed paper info including abstract, DOI, authors
  • Perform structured PICO searches with synonym support

Use cases of PubMed Enhanced Search Server

  • Conduct literature searches for systematic reviews
  • Compare publication prevalence across multiple medical topics
  • Perform structured evidence-based searches using the PICO framework
  • Retrieve detailed metadata and abstracts for specific papers by PMID

よくある質問

1

What are the prerequisites to run the server?

Python 3.6 or later and pip. The dependencies `fastmcp` and `requests` must be installed via pip.

2

How do I install the server?

Clone the repository, then run `pip install fastmcp requests` in the project directory.

3

What MCP functions does the server provide?

Five functions: `search_pubmed`, `get_mesh_terms`, `get_pubmed_count`, `format_paper_details`, and `pico_search`. Each accepts specific parameters and returns structured data.

4

How does the server handle NCBI rate limiting?

The server implements an automatic retry mechanism with backoff delays to handle potential rate limiting by NCBI's E-utilities service.

5

What license is this project under?

The project is licensed under the BSD 3-Clause License. See the LICENSE file for details.

コメント

「データと分析」の他のコンテンツ

Instagram MCP Server

HasData

Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.

23

TikTok MCP Server

HasData

Hosted TikTok MCP server for AI agents: read public profiles, account videos, comments and replies, or search videos and creators. Structured JSON for creator research and content analysis.

3

Subtext

Subtext by Fullstory

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can

9

Trendos

Gintare Rimolaityte

Trendos is a remote MCP server for AI search visibility data and opportunities available at https://api.trendos.com.

hedwigai

hedwigai

Research workbooks your agent keeps current: spreadsheets and memos where every figure cites its primary source (SEC filings, customs records, trial registries), plus data programs such as website traffic for 1,000 domai

広告掲載