pubmed-mcp-server
This server allows users to search PubMed for article abstracts asynchronously based on specified queries.
Search PubMed: Query PubMed for articles using specific search terms
Retrieve Abstracts: Fetch and return article abstracts
Asynchronous Execution: Perform searches without blocking the server
Customizable Parameters: Specify search queries and limit the number of results returned
Formatted Output: Receive abstracts as a string with proper separation between entries
Enables searching PubMed for scientific articles and retrieving their abstracts with customizable query parameters and result limits.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pubmed-mcp-server search for recent articles on CRISPR gene editing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PubMed MCP Server
This repository contains an MCP server that searches PubMed for article abstracts using BioPython's Entrez module. It leverages the FastMCP framework to provide asynchronous search capabilities for PubMed.
Features
Search PubMed: Query for articles based on a search term.
Retrieve Abstracts: Fetch abstracts of articles returned from PubMed.
Asynchronous Operation: Uses asynchronous execution (via
asyncio.to_thread) to avoid blocking the server.
Related MCP server: PubMed MCP Server
Prerequisites
Python 3.8 or higher
mcp[cli]
BioPython
Setup
Clone the Repository:
git clone https://github.com/AIAnytime/MCP-Servers cd pubmed-mcp-serverInstall Dependencies:
You can install the required packages using uv:
uv add -r requirements.txtConfigure Entrez Email:
Ensure you have set a valid email address in the code (in
main.py):Entrez.email = "give an email address"
Running the Server
Start the PubMed MCP server by running:
uv run main.pyThis command starts the server using the uv command-line tool (as specified in your configuration).
Configuring the MCP Client
To configure your MCP client to connect to the PubMed MCP server, create or update your config.json file as follows:
{
"mcpServers": {
"pubmed": {
"command": "C:/Users/aiany/.local/bin/uv",
"args": [
"--directory",
"C:/Users/aiany/OneDrive/Desktop/YT Video/pubmed-mcp-server",
"run",
"main.py"
]
}
}
}Explanation of the Configuration
command:
The full path to the command-line tool used to run the MCP server (in this case,uv).args:
--directory: Specifies the working directory where the server is located."C:/Users/aiany/OneDrive/Desktop/YT Video/pubmed-mcp-server": The path to the server's root directory."run"and"main.py": The command and entry point to start the PubMed MCP server.
Usage
Once the server is running and your MCP client is configured, you can use the provided tool:
Tool:
search_pubmedParameters:
query: The search term for PubMed (default is"endocarditis").max_results: Maximum number of articles to retrieve (default is10).
Example Usage:
search_pubmed(query="endocarditis", max_results=10)This will return a string with the abstracts of the articles separated by newlines.
License
This project is licensed under the MIT License.
You can adjust paths and details as needed for your specific setup.
Available Tools
1 toolsearch_pubmedB
Search PubMed for articles matching the query.
Args:
query: The search term for PubMed.
max_results: Maximum number of articles to retrieve.
Returns:
A string containing the abstracts of found articles, separated by two newlines.
Inputs: max_results, query.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool 'search_pubmed' has a clear, singular purpose of searching PubMed for articles, making disambiguation trivial.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'search_pubmed' follows a clear verb_noun pattern, and there are no other tools to compare it against for inconsistency.
A single tool for a PubMed server is too few for the apparent scope. PubMed typically involves operations like fetching article details, filtering by date or author, or retrieving citations, which are missing. This minimal set limits functionality and feels incomplete for the domain.
The tool set is severely incomplete for a PubMed server. While 'search_pubmed' covers basic searching, there are obvious gaps such as retrieving full article metadata, accessing citations, filtering results, or managing user queries. This will likely cause agent failures when more complex tasks are required.
Maintenance
Related MCP Connectors
Search PubMed biomedical literature and fetch structured article records.
Search 36M+ PubMed biomedical articles and ClinicalTrials.gov studies.
Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms.
Search PubMed, read abstracts and summaries, and find similar articles in NCBI PubMed.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables searching and retrieving detailed information from PubMed articles using the NCBI Entrez API. Supports configurable search parameters including title/abstract filtering and keyword expansion to find relevant scientific publications.1-
- AlicenseBqualityDmaintenanceEnables AI assistants to search and retrieve biomedical research articles from PubMed's database of over 35 million citations, including metadata, abstracts, MeSH terms, and full-text PDFs when available.11MIT
- FlicenseNot gradedqualityCmaintenanceEnables searching PubMed's biomedical literature database and retrieving article metadata, abstracts, and full content through the E-utilities API. Supports advanced queries, batch operations, and multiple output formats with automatic rate limiting.2-
- AlicenseNot gradedqualityCmaintenanceEnables searching and retrieving biomedical literature from PubMed via the NCBI E-utilities API.112 npm1MIT