advanced_search
Perform advanced PubMed searches with multiple criteria.
LABSCO SUMMARY
PubMed becomes something you can hold a conversation with, including the parts that only work if you know the vocabulary.
The sequence that pays off is search, then details, then related articles — and search_mesh_terms before all of it when terminology matters, because the right Medical Subject Heading finds papers a plain keyword misses entirely. Get an NCBI API key before doing anything at volume: it takes the rate limit from 3 requests per second to 10.
What it is
An MCP server over NCBI's PubMed APIs for literature work, with caching, rate limiting and batch processing built in for volume searching.
What you get
- search_pubmed with a sort order, a date range and a result cap
- advanced_search that combines terms, authors, journals and publication types with a boolean operator and a date window
- get_article_details for a set of PMIDs — abstracts, author lists, MeSH terms, DOIs and publication information
- get_related_articles to follow NCBI's own relatedness outward from one paper
- search_mesh_terms so you can find the right Medical Subject Heading before you search with it
- Batch tools for scale: several queries run in parallel, and long PMID lists fetched in chunks
- A response cache with statistics and a way to clear expired entries
- Analytics on usage, performance and system health, with a configurable time window and a reset
Requirements
Python 3.8 or higher. The package is published as ncbi-mcp-server with an entry point of the same name; the repository's own setup runs it from the project directory under Poetry. No credentials are strictly required, but an NCBI API key and email raise the ceiling: 3 requests per second without a key, 10 with one. Both go into a .env file alongside the server.
Setup effort
One command — uvx ncbi-mcp-server
USE CASES
01
Starting a literature review from a topic
Search the database, then pull abstracts and metadata for the results worth reading.
02
Getting the terminology right before searching
Find the Medical Subject Heading for the concept, then build the query around it.
03
Following one key paper outward
Fetch the articles NCBI considers related, then read their details.
04
Narrowing to particular authors, journals or study types
Combine the criteria with a boolean operator and a date window in one call.
05
Working through a long reference list
Hand over all the PMIDs at once and let them be fetched in chunks.
06
Running several angles on a topic at once
Submit the queries together and get the result sets back in parallel.
12 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
batch_get_article_details
Fetch article details for many PMIDs efficiently in batches.
batch_search_multiple_queries
Perform multiple PubMed searches in parallel for efficiency.
cache_stats
Get cache performance statistics.
clear_cache
Clear expired cache entries.
get_analytics_summary
Get comprehensive analytics summary including usage stats, performance metrics, and system health.
get_article_details
Fetch detailed information for specific PubMed articles.
get_detailed_metrics
Get detailed performance metrics for the specified time period (default: last 24 hours).
get_related_articles
Find articles related to a specific PubMed article.
reset_analytics
Reset analytics data (use with caution - this will clear all collected metrics).
search_mesh_terms
Search Medical Subject Headings (MeSH) terms.
search_pubmed
Search PubMed database for scientific literature.
BEFORE YOU INSTALL
What to know first
Tools you get
12 tools when we connected. batch_search_multiple_queries, batch_get_article_details and clear_cache are available but undocumented.
Requires
- uvx on PATH
- Python 3.8
- Redis Commander UI
Where it runs
The documented client runs the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 12 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx ncbi-mcp-serverMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"ncbi-literature": {
"command": "poetry",
"args": [
"run",
"python",
"src/ncbi_mcp_server/server.py"
],
"cwd": "<YOUR_PATH_TO_NCBI_MCP_SERVER>"
}
}
}
