PubMed Analysis MCP Server

@Darkroaster

About PubMed Analysis MCP Server

A PubMed MCP server.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "pubmearch": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "-e",
        "."
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is PubMed Analysis MCP Server?

A professional MCP server for analyzing PubMed medical literature. It helps researchers quickly gain insights into medical research dynamics by supporting advanced search syntax, keyword frequency analysis, trend tracking, publication counts, and comprehensive report generation.

How to use PubMed Analysis MCP Server?

Install dependencies using uv pip install -e . in the pyproject.toml directory. Configure the MCP server in mcp.json with the command uv run --directory path/to/project -m pubmearch.server, and set environment variables NCBI_USER_EMAIL and NCBI_USER_API_KEY. Use the provided tools (e.g., search_pubmed, analyze_research_keywords) via LLM prompts.

Key features of PubMed Analysis MCP Server

Literature retrieval with PubMed advanced search syntax and date filtering.
Hotspot analysis: keyword frequency and popular research area identification.
Trend tracking: keyword frequency changes over time.
Publication count analysis with customizable time periods.
Comprehensive reports: one-click generation of hotspot, trend, and statistics.

Use cases of PubMed Analysis MCP Server

Identify research hotspots on a specific medical topic (e.g., prostate cancer immunotherapy).
Track how research trends evolve over custom date ranges.
Generate a full analytical report of publication volume and keyword dynamics.
Retrieve and save PubMed search results for offline review.

FAQ from PubMed Analysis MCP Server

What dependencies are required?

Python environment with uv is recommended. The server requires NCBI API credentials (NCBI_USER_EMAIL and NCBI_USER_API_KEY).

How are search results stored?

Results are saved in the pubmearch/results directory; logs are in pubmed_server.log.

What is the default maximum number of search results?

The default max_results for search_pubmed is 1000.

Is there any usage policy to follow?

Yes, you must follow NCBI's API usage policies.

What license does the project use?

MIT license.

Frequently asked questions

What dependencies are required?

Python environment with `uv` is recommended. The server requires NCBI API credentials (`NCBI_USER_EMAIL` and `NCBI_USER_API_KEY`).

How are search results stored?

Results are saved in the `pubmearch/results` directory; logs are in `pubmed_server.log`.

What is the default maximum number of search results?

The default `max_results` for `search_pubmed` is 1000.

Is there any usage policy to follow?

Yes, you must follow NCBI's API usage policies.

What license does the project use?

MIT license.

Comments

Basic information

More Data & Analytics MCP servers

Bright Data MCP

luminati-io

A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.

2.5K

MCP Server for Data Exploration

reading-plus-ai

544

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

Opinly

Track competitors, rankings, and how AI answers rank you — then write and publish the fix.

Rankbits

rankbits

AI visibility analytics across 15+ providers (ChatGPT, Perplexity, Gemini, AI Overviews, and more). The MCP connector lets assistants run scans, compare competitor mentions, and track your brand's visibility in AI answer