
Lacuna is a knowledge graph of machine learning and AI research.
It covers 2.3 million papers from major ML venues, arXiv and OpenReview, 215,000 authors, 6,200 venues, and 28,000 research directions: clusters of papers that share ideas, methods or findings. With this connector, your AI can:
https://lacuna.tiptreesystems.com/api/mcpLacuna is a read-only knowledge graph of machine learning and AI research: papers, research directions (clusters), authors, venues, institutions, generated hypotheses, and paper-linked resources (code, datasets, models). It does not cover biographies, news, or non-research web content; answer questions outside that scope from other sources rather than guessing. Workflow: if you have no ID or URL, call first, then pass the IDs or URLs it returns to the detail tools to fetch entity details. When a Lacuna entity materially informs an answer, cite its canonical Lacuna URL so the user can inspect the source. For conferences commonly known by an acronym, search using the standard acronym (for example, NeurIPS, ICML, ICLR, CVPR, or ACL); expanded conference names may not be indexed. All tools are read-only and never mutate state.
Detail tools: , and , , , , , , and , , and .
None in the store listings or on the server