Skip to main content
Glama
cyanheads

pubmed-mcp-server

by cyanheads

Pubmed Search Articles

pubmed_search_articles
Read-only

Search PubMed using full query syntax, apply filters by author, journal, MeSH terms, date ranges, and more. Returns PMIDs with optional summaries, supporting pagination.

Instructions

Search PubMed with full query syntax, filters, and date ranges. Returns PMIDs and optional brief summaries. Supports field-specific filters (author, journal, MeSH terms), common filters (language, species, free full text), and pagination via offset for paging through large result sets.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoSort order: relevance (default), pub_date (newest first), author, or journalrelevance
queryYesPubMed search query (supports full NCBI syntax)
authorNoFilter by author name (e.g. "Smith J")
offsetNoResult offset for pagination (0-based). PubMed serves at most the first 9999 records of a result set, so this caps at 9998; narrow the query or add filters to reach anything beyond it.
journalNoFilter by journal name
speciesNoFilter by species
languageNoFilter by language (e.g. "english")
dateRangeNoFilter by date range. The filter is applied only when both `minDate` and `maxDate` are non-empty; either one empty disables the entire date range.
meshTermsNoFilter by MeSH terms. Multiple terms are AND'd — all must match.
maxResultsNoMaximum results to return
hasAbstractNoOnly include articles with abstracts
freeFullTextNoOnly include free full text articles
summaryCountNoFetch brief summaries for top N results (0 = PMIDs only). Above the 50 cap, pass the remaining PMIDs to pubmed_fetch_articles.
publicationTypesNoFilter by publication type (e.g. "Review", "Clinical Trial", "Meta-Analysis"). Multiple values are OR'd — any match qualifies.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pmidsYesPubMed IDs
queryYesOriginal query
noticeNoOptional guidance when the result set does not reflect what was asked for — a field tag PubMed ignored, a phrase it matched nothing for, a dateRange dropped for having one bound, no matches at all, or paging past the end. Absent when nothing applies.
offsetYesResult offset used
searchUrlYesPubMed search URL
summariesYesBrief summaries (empty array when summaryCount is 0)
totalCountYesTotal matching articles
appliedFiltersYesNormalized filter values that were applied to the PubMed query
effectiveQueryYesSanitized query sent to PubMed after applying all active filters
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses important behaviors beyond annotations: it returns 'PMIDs and optional brief summaries,' supports pagination via offset, and notes that PubMed caps results at 9999 records. It also explains that summary counts >50 should be handled by another tool. These details add significant context to the readOnlyHint and openWorldHint annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loading the core purpose and then enumerating supported features concisely. Every sentence adds value, and there is no redundant or irrelevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 14 parameters, nested schemas, and an output schema, the description covers the main capabilities (query syntax, filters, date ranges, pagination, optional summaries). It also provides cross-tool guidance for large summaries. However, it does not mention that the query supports full NCBI syntax (though implied) or briefly describe the output format, but the output schema covers that. Still, it is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with comprehensive parameter descriptions. The tool description summarizes the filter types but does not add new semantic details beyond what the schema already provides. Per guidelines, with high schema coverage, baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Search PubMed with full query syntax, filters, and date ranges' and specifies that it 'Returns PMIDs and optional brief summaries.' This verb+resource combination is specific and distinguishes the tool from siblings like pubmed_fetch_articles or pubmed_fetch_fulltext, which retrieve data for given IDs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what the tool does but does not explicitly state when to use it vs. alternatives. It mentions pagination and the summaryCount cap (suggesting use of pubmed_fetch_articles for larger summaries), which provides some guidance, but no direct comparison to other tools or conditions for choosing this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cyanheads/pubmed-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server