Skip to content

MCP Endpoints

Valency MCP provides 32 endpoints organized into 8 categories. Once connected, your AI assistant can use any of these tools. Try some example prompts.

EndpointDescription
semantic_search_papersSearch by meaning using semantic embeddings
search_by_titleFind papers by title keywords
search_by_abstractFind papers by abstract content
search_by_authorFind papers by author name (literal string matching)
search_by_categoryFind papers in a research domain (recency-ordered)
search_by_venueSearch by publication venue (journal or conference)
search_cross_categorySearch abstracts across multiple categories
find_similar_papersFind semantically similar papers to a given paper
get_citing_papersFind papers that cite a given paper
EndpointDescription
filter_by_categoriesFilter across multiple domains (recency-ordered)
filter_by_date_rangeFilter by publication date
filter_by_licenseFilter by license type (CC-BY, CC0, arxiv default, etc.)
filter_papers_with_doiFind papers with DOI identifiers
count_papersCount papers matching filters (number only)
EndpointDescription
get_author_profileComprehensive researcher summary profile
find_coauthorsFind an author’s most frequent collaborators
compare_authorsCompare 2–10 researchers side by side
batch_author_categoriesCategory distributions for multiple authors
identify_prolific_authorsRank authors by publication count
EndpointDescription
get_paper_by_idDirect lookup by paper ID
get_paper_versionsRevision history for a paper
EndpointDescription
get_keyword_trendsPaper counts over time for a keyword/abstract search
get_publication_trendsPaper counts over time for a category
get_publication_trends_batchTrends for multiple categories in one call
analyze_corpus_metricsCorpus-wide descriptive statistics
identify_research_domainsRank research domains by volume
get_field_coverageMost common values for a metadata field
EndpointDescription
list_sourcesAvailable paper sources with counts and date ranges
EndpointDescription
export_papers_csvExport papers to CSV
export_papers_jsonExport papers to JSON
export_from_filterExport papers matching a filter as in-memory content
EndpointDescription
submit_feedbackSubmit feedback about search quality, bugs, or feature requests

Once you’ve connected Valency to your AI assistant, you can start using these endpoints immediately through natural language.

Semantic search:

“Search for papers about transformer attention mechanisms”

Author research:

“Show me Geoffrey Hinton’s publication profile” “Who are Yann LeCun’s most frequent collaborators?”

Trends:

“What are the publication trends for machine learning over the last 5 years?”

Filtering:

“Find papers about climate change from 2023 with CC-BY license”

Export:

“Export the top 100 papers about CRISPR to CSV”

  • Be specific: More specific queries return better results
  • Combine endpoints: Your AI assistant can chain multiple endpoints together
  • Use filters: Narrow results by date, license, or category
  • Try semantic search first: semantic_search_papers often gives the best results for exploratory queries