Search 17M+ biomedical journal abstracts (13M+ in PubMed) by meaning or by exact terms.
Scored across 2 tools
The two tools are clearly differentiated by search mode: semantic meaning vs exact keyword/Boolean matching. The descriptions explicitly state when to use each, including concrete examples like gene symbols and variants, so an agent can reliably choose.
Both names follow a consistent search_corpus prefix with a clear modifier suffix. The pattern is predictable, though the longer keyword variant is a minor deviation from a strict verb_noun form.
Two tools is thin for a scholarly search server, even if each mode earns its place. The surface is narrowly scoped to retrieval, leaving little room for adjacent operations.
Search coverage is strong, with rich filters and metadata, but there is no direct get-by-ID tool, citation traversal, related-paper discovery, or full-text access. Agents can work around some gaps via filters, but lifecycle coverage is limited.
Semantic search over 11M+ biomedical journal abstracts (more than 7 million of them in PubMed). Finds papers by MEANING, not keywords. Returns papers ranked by a hybrid relevance score (semantic similarity + lexical overlap + citation quality + recency) with abstracts, PMIDs, metadata and DOI links. Supports filters: year range, open access, citations, article type, journal, language, author name, DOI, PMID, and title search.
Inputs: query (required), doi, pmid, topK, +10 more.
KEYWORD/Boolean search over the same 11M+ biomedical abstracts, matching EXACT TERMS rather than meaning. Use this instead of search_corpus when the query contains specific identifiers — gene symbols (TP53, BRCA1), variants (p.Gly12Asp, c.35G>A, rs334), accessions, clinical-trial IDs (NCT…), cell lines, drug codes — or when you want PubMed-style Boolean logic. Vector search loses the exact identity of rare strings, so keyword mode is substantially better for these queries and worse for open natural-language questions. Syntax: terms are ANDed by default; AND / OR / NOT are supported; prefix a term with - to exclude it; use "quoted phrases" for exact adjacent wording. A very broad query is ranked over its best BM25 matches.
Inputs: query (required), doi, pmid, topK, +10 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Search 36M+ PubMed biomedical articles and ClinicalTrials.gov studies.
Search PubMed with precision using keyword and journal filters and smart sorting. Uncover MeSH ter…
Search biomedical papers, inspect publication records, and traverse citation or semantic graphs.
Search PubMed, read abstracts and summaries, and find similar articles in NCBI PubMed.
Add one secure layer between your agents and this server.