Pubcrawl
PubCrawl is an MCP server that provides LLM clients with access to PubMed literature retrieval, FDA drug labels, UK drug data, and ClinicalTrials.gov clinical trials, enabling comprehensive medical information queries from literature to labels to trials.
2.5 points
8.3K

What is PubCrawl?

PubCrawl is an intelligent assistant specifically designed for medical research. Through the Model Context Protocol (MCP) technology, it allows AI assistants (such as Claude) to directly access authoritative medical databases, including: • PubMed - The world's largest biomedical literature database • FDA drug labels - Official drug information from the U.S. Food and Drug Administration • UK drug data - UK electronic medicine compendium (eMC) • ClinicalTrials.gov - The global clinical trial registration database In simple terms, PubCrawl equips AI with professional medical literature retrieval and analysis capabilities.

How to use PubCrawl?

Using PubCrawl is very simple: 1. Install PubCrawl on your AI assistant (such as Claude Desktop) 2. Configure the connection information 3. Have a conversation with the AI as usual, but now you can ask professional medical questions For example, you can directly ask: "What are the recent important studies on new diabetes drugs?" or "Show me the drug label of aspirin." The AI will obtain the latest and most accurate information through PubCrawl to answer you.

Use cases

PubCrawl is particularly suitable for the following people and scenarios: • Medical researchers - Quickly find relevant literature and clinical trials • Clinicians - Look up drug labels and the latest treatment guidelines • Medical students - Learn about drug information and disease research progress • Pharmaceutical industry personnel - Track competitor information and regulatory requirements • Patients and their families - Understand the latest progress in disease treatment Whether you are a professional or an ordinary user, as long as you need reliable medical information, PubCrawl can provide assistance.

Main features

Medical literature retrieval
Intelligently search the PubMed database and filter by conditions such as date range, article type, and journal impact factor. Return search results with complete information including title, author, journal, DOI, etc.
Structured abstract analysis
Obtain the complete structured abstract of a paper, automatically divide it into sections such as background, methods, results, and conclusions, and extract keywords and MeSH terms for easy and quick understanding of the research content.
Full-text access
Retrieve the full text of open-access articles in PubMed Central, automatically parse the article structure, figure descriptions, and references, and provide complete academic content.
Related literature recommendation
Use PubMed's similarity algorithm to find related articles and sort them by relevance to help you discover more related research.
Citation format generation
Automatically generate standardized citations in multiple formats such as APA, Vancouver, Harvard, and BibTeX, saving time for literature organization.
Hot paper tracking
Find the latest important papers on a specific topic and filter high-impact journals (such as Nature, Science, NEJM, etc.).
Drug label query
Obtain the official FDA drug labels (USPI) and UK drug labels (SmPC), including complete information such as indications, usage and dosage, warnings, and contraindications.
Cross - national drug information comparison
Compare the regulatory differences between the United States and the United Kingdom for the same drug, including different requirements in aspects such as indications, warnings, and dosages.
Search for drugs by indication
Find approved drugs based on diseases or symptoms and provide both FDA and UK regulatory information.
Clinical trial search
Search the ClinicalTrials.gov database and filter clinical trials by conditions such as disease, intervention, recruitment status, and trial phase.
Clinical trial details
Obtain the complete information of a clinical trial, including inclusion criteria, study design, grouping, primary/secondary endpoints, study locations, etc.
Advantages
One - stop medical information query: Integrate multiple authoritative databases without switching between different websites
Natural language interaction: Ask questions in daily language without learning complex retrieval syntax
Real - time update: Obtain the latest research progress and regulatory information
Multi - national regulatory comparison: View the drug regulatory differences between the United States and the United Kingdom simultaneously
Free to use: Basic functions are completely free without subscription fees
Easy to integrate: Easily integrate into mainstream AI assistants such as Claude
Limitations
Some full - text access is restricted: The full text of some journals may require a subscription to access
API rate limit: A maximum of 3 requests per second without an API key
Dependent on network connection: Requires a stable Internet connection
Language limitation: Mainly supports English content, and the content in other languages is limited
Data delay: There may be a 1 - 2 day delay in the update of some databases

How to use

Install the Node.js environment
Ensure that your computer has Node.js 20 or a higher version installed. You can download the installation package from the Node.js official website.
Install PubCrawl
Install PubCrawl globally via npm (Node.js package manager).
Configure the AI assistant
Configure according to the AI assistant you are using. Taking Claude Desktop as an example, you need to edit the configuration file. macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json
Restart and start using
Restart your AI assistant, and PubCrawl will appear in the connector list. Now you can start asking medical questions!
(Optional) Obtain an API key
If you need a higher request frequency, you can register a free NCBI account to obtain an API key.

Usage examples

Clinician queries drug information
Dr. Zhang encounters a patient who needs to use a new drug in the outpatient clinic and needs to quickly understand the detailed information, indications, and precautions of the drug.
Researcher conducts a literature review
Researcher Li is preparing a review article on CAR - T cell therapy and needs to find the latest important research and clinical trial progress.
Medical student studies a course
Medical student Wang is studying cardiovascular pharmacology and needs to compare the characteristics and international regulatory differences of different statins.
Patient understands treatment options
Mr. Zhao has been diagnosed with type 2 diabetes and wants to know what approved drugs are available for treatment.

Frequently Asked Questions

Is PubCrawl free?
Do I need programming knowledge to use it?
Does PubCrawl support Chinese search?
How timely is the data update?
Can I trust the accuracy of this information?
Is an API key necessary?
Can PubCrawl replace a doctor's advice?
Which AI assistants are supported?

Related resources

PubCrawl GitHub repository
View the source code, report issues, or contribute code
Model Context Protocol official website
Understand the technical principles and specifications of MCP
PharmaTools.AI official website
The official website of the PubCrawl development team
PubMed official website
The official interface of the PubMed database
ClinicalTrials.gov
The global clinical trial registration database
FDA DailyMed
The official database of FDA drug labels
UK eMC
The official database of UK drug labels
NCBI account registration
Register a free NCBI account to obtain an API key

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "pubcrawl": {
      "command": "pubcrawl"
    }
  }
}

{
  "mcpServers": {
    "pubcrawl": {
      "command": "node",
      "args": ["/path/to/pubcrawl/dist/index.js"]
    }
  }
}

{
  "mcpServers": {
    "pubcrawl": {
      "command": "pubcrawl",
      "env": {
        "NCBI_API_KEY": "your_key_here"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

P
Paperbanana
Python
9.1K
5 points
F
Finlab Ai
FinLab AI is a quantitative financial analysis platform that helps users discover excess returns (alpha) in investment strategies through AI technology. It provides a rich dataset, backtesting framework, and strategy examples, supporting automated installation and integration into mainstream AI programming assistants.
10.0K
4 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
9.1K
5 points
P
Praisonai
PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.
Python
16.8K
5 points
M
Maverick MCP
MaverickMCP is a personal stock analysis server based on FastMCP 2.0, providing professional level financial data analysis, technical indicator calculation, and investment portfolio optimization tools for MCP clients such as Claude Desktop. It comes pre-set with 520 S&P 500 stock data, supports multiple technical analysis strategies and parallel processing, and can run locally without complex authentication.
Python
12.0K
4 points
K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
36.2K
5 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
24.1K
5 points
A
Apple Health MCP
An MCP server for querying Apple Health data via SQL, implemented based on DuckDB for efficient analysis, supporting natural language queries and automatic report generation.
TypeScript
13.4K
4.5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.1K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
82.2K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
38.3K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
27.6K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
38.6K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
71.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
55.6K
4.8 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
25.2K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase