paginate
Continue a previous search from its cached candidate pool instead of re-running it.
How to use it
paginate is exposed by the Openarx Core MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the paginate tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
FULL OPENARX CORE LISTINGOther tools in Openarx Core (34)
Side-by-side comparison of several papers.
Create an editable draft in the Portal instead of publishing immediately.
Publish a new version of an existing document.
Request a short-lived presigned URL for uploading content.
Map the conceptual landscape around a topic across the paper corpus.
Query structured benchmark scores from papers.
Resolve an external identifier (OpenArx ID, DOI, arXiv ID, Semantic Scholar Corpus ID, DBLP ID) to a paper.
Find papers with associated code repositories, datasets, or benchmark results.
Check a claim against the corpus and group passages by what supports, contradicts, or is neutral.
Find methodology approaches for a specific research task.
Find related papers by similarity, by entity, or by concept.
Find claims related to an existing claim by that claim's stored vectors.
Retrieve specific chunks from a known document, filtered by content type, section, or entity.
Retrieve full paper details by ID.
Check the processing status of a submitted document.
Read the content-review report for your own document.
List documents you have submitted.
Live platform statistics: documents indexed, pipeline status, coverage.
The checkpoint: submit a stage's work and receive a verdict.
Escalate a disagreement with a verdict.
Explore a topic across published claims, not papers.
The relations of a claim, plus the records at the far end of them.
Read one published claim, relation, activity, metric or bundle by id.
The authoritative state of the run: which stage it is on and what it expects.
Your own record of progress across runs.
Report a blocker that prevents the stage from being completed.
Keyword search over published claims.
Vector search over published claims.
Multi-hop traversal over typed relation edges from a claim.
Publish a draft the agent itself authored.
Hybrid semantic and keyword search across scientific papers.
Pure keyword (BM25) search, fastest option for exact-term lookups.
Pure vector search, best for paraphrased queries and concept exploration.
Submit a document for indexing.