Lacuna Research MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LACUNA_SITE_URL | No | Base URL of the Lacuna instance. | https://lacuna.tiptreesystems.com |
| LACUNA_MCP_TIMEOUT | No | Timeout in seconds for API requests. | 30 |
| LACUNA_MCP_LOG_LEVEL | No | Log level (DEBUG, INFO, WARNING, ERROR, CRITICAL). | WARNING |
| LACUNA_MCP_USER_AGENT | No | User-Agent header to use. | lacuna-research-mcp/{package_version} |
| LACUNA_MCP_MAX_RETRIES | No | Maximum number of retries for failed requests. | 2 |
| LACUNA_MCP_BEARER_TOKEN | No | Optional bearer token for private Lacuna deployments. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Lacuna is a read-only knowledge graph of machine learning and AI research from Tiptree Systems: papers, research directions (clusters), authors, venues, institutions, generated hypotheses, and paper-linked resources (code, datasets, models). Workflow: call search_lacuna first, then pass the IDs or URLs it returns to the detail tools. When a Lacuna entity materially informs an answer, cite its canonical Lacuna URL so the user can inspect the source. All tools are read-only and never mutate state.
Scope: ML and AI research. Lacuna has no reference lists or citation graph, and it does not cover biographies, news, or non-research web content; answer those from other sources rather than guessing. 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.
Choose the route by the question. When the question is about people or a field, do not stop at a list of papers:
One known paper (arXiv ID, DOI, or an arXiv, DOI or OpenReview URL): get_paper accepts these directly. Its default view is a summary; view="fulltext" reads the paper itself.
Literature on a topic: search_lacuna(search_type="paper"), then get_paper on the few results that matter.
Who works on a topic: search_lacuna(search_type="cluster") to find the research direction, then get_direction for its leading authors. Use get_author_context for one person and get_author_neighbors for similar researchers.
What a university, lab or company publishes: search_lacuna(search_type="institution"), then get_institution_context.
What a venue published: search_lacuna(search_type="venue"), then get_venue_context, optionally for one year.
Where a field is heading: get_direction for the map of a direction and its neighbors; search_lacuna(search_type="hypothesis") and get_hypothesis for open research ideas.
Code, datasets or models: search_lacuna(search_type="resource"), then get_resource for the papers that use them.
Keep calls small. Default views are compact; request a full view only when a field you need is missing. One well-phrased search is better than several paraphrases of it.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_lacunaA | Search Lacuna's ML/AI corpus for papers, research directions, authors, venues, institutions, novel research hypotheses, and research resources (code repositories, datasets, models, and demos linked to papers). Start here for any question without an ID. Set search_type to what the question is about: paper for literature; cluster for a research direction ("who works on X", "what is the state of X"); author, institution or venue for a person, a lab or a conference; hypothesis for open research ideas; resource for code, datasets and models. Then pass a result's id or url to the matching detail tool. A query that is an arXiv ID, a DOI, or an arXiv, DOI or OpenReview URL
returns that exact paper. Paper results carry For novel ML/AI research ideas, use search_type="hypothesis", then get_hypothesis on promising results. search_type accepts all, cluster, paper, author, institution, venue, hypothesis, or resource. Use paper for literature and get_paper to read a result. Use other sources for biographies, news, and non-research web content. Resources: search_type="resource" searches GitHub repositories, Hugging
Face datasets/models, and Zenodo records that Lacuna has linked to at least
one paper. To find benchmark or evaluation datasets, use
search_type="resource" with resource_kind="dataset" (for example query
"image classification benchmark" or a dataset name like "ImageNet").
resource_kind accepts codebase, dataset, model, or demo (one value or a
list); provider accepts github, huggingface, or zenodo. Both filters require
search_type "resource" or "all" (with either filter set, only resources are
returned). Each result has an external ranking_profile accepts:
sort accepts relevance (default), year_desc, or year_asc. Semantic ranking cannot use year sorting; constrain recency with date_from/date_to instead. date_from and date_to are inclusive YYYY, YYYY-MM, or YYYY-MM-DD bounds. author_id_or_url constrains a paper search to one author. Pass an author ID or Lacuna author page URL; it requires search_type="paper". fields optionally restricts and weights lexical fields, for example "title^4,abstract". Supported names are title, abstract, summary, concepts, name, top_names, and venue, plus description, topics, provider_key, and paper_titles for resources (a resource's title already includes its description, topics, README text, and linked paper titles). Fields must exist on the selected search_type, weights must be within 0 < weight <= 100, and fields cannot be combined with semantic ranking. |
| get_hypothesisA | Fetch a generated novel ML/AI research proposal from Lacuna. Use after search_lacuna(search_type="hypothesis") to inspect a proposal. view selects the response shape:
|
| get_directionA | Describe one research direction: what it is, who leads it, what is nearby. Use for "who works on X", "what is the state of X" and "what is adjacent to X", after search_lacuna(search_type="cluster") finds the direction. The context names the direction's leading authors, key papers and related directions. Use a numeric cluster ID (for example 25005) or a direction URL ending in that number. view selects the response shape (
|
| get_direction_papersA | Fetch paginated papers associated with a Lacuna research direction/cluster. view selects the per-paper shape:
|
| get_paperA | Fetch one paper: its summary, authors, venue, figures, linked resources, or full text. Accepts a Lacuna artifact ID or paper URL from search_lacuna, or an outside
identifier for the same paper: an arXiv ID (2310.06825), a DOI, or an
arXiv, DOI or OpenReview URL. Use this when the user names a specific paper
or after a search. For an outside identifier that is not in Lacuna's ML/AI
corpus, the result is include_resources adds linked resources (code repositories, datasets, models, and demos) in context and full views by default. Pass False to omit them; other views ignore this option. Pass a resource entry's id to get_resource for further details. view selects the response shape.
figure_limit (context view only) caps the figure preview (server default 3).
Pass 0 to suppress figure previews while keeping a |
| get_resourceA | Fetch a Lacuna research resource (code repository, dataset, model, or demo). Accepts a resource artifact ID (art_...) or a Lacuna resource URL containing that ID (/resource//art_...). The response includes the external url, a summary, facets (tasks, modalities,
size, license, access), provider metrics, a README/card excerpt,
|
| get_author_papersA | List what one author has published, newest first, one page at a time. Use for "what has X worked on recently". Pass an author id or URL from search_lacuna(search_type="author") or from any paper's author list. |
| get_author_directionsA | List the research directions one author publishes in, one page at a time. Use for "what areas does X work in" or to check whether a person is active in a given direction. Pass an author id or URL. |
| get_author_contextA | Profile one researcher: their main papers and the directions they shaped. Use for "who is X in research terms" or "what is X known for". Author profiles describe research output (papers, directions, impact). A
free-text view selects the response shape:
Set include_neighbors=True to include similar authors as named, linkable records. Neighbor computation may add significant server latency. |
| get_author_neighborsA | List researchers whose work is closest to one author's, ranked. Use for "who else works on what X works on": finding possible collaborators, reviewers or related groups. Pass an author id or URL. |
| get_venue_contextA | Describe a conference or journal: its top authors and directions, by year. Use for "what did NeurIPS 2025 focus on" or "who publishes most at X". Venue keys are opaque hashes (e.g. "d7bf22905bd6"), never human-readable names like "icml". Find the key first via search_lacuna(search_type="venue") or pass a /venue/... page URL. view selects the response shape:
|
| get_institution_contextA | Describe the research output of a university, lab or company. Use for "what does X publish" or "who are the most active authors at X". The context summarizes the institution's research output: its paper and author counts and the authors who publish most often under it. Affiliations come from the author affiliations listed on published papers, not from staff directories, and may be incomplete or out of date. The response has no contact details, biographies or employment records. view selects the response shape:
Use get_institution_authors to page through the complete author list. |
| get_institution_authorsA | Fetch one page of authors who list a Lacuna institution on their papers. Each author appears because published papers list this institution as one of their affiliations. This is a record of research output, not a staff directory: it may be incomplete or out of date and does not show current employment. Each entry has the author's name, Lacuna page and paper count; there are no contact details or other personal data. Results are ordered by paper count. Use authors_total, authors_returned, authors_offset, and authors_truncated to page through the complete list. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| prior_work | Check prior ML/AI work for a proposed method, experiment or idea. |
| research_map | Map what has been tried on an ML/AI research topic and what is still open. |
| find_researchers | Find ML/AI researchers working on a topic. |
| paper_context | Explain an ML/AI paper and place it among related work. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Each tool maps to a distinct entity+action (paper, direction, author, venue, institution, resource, hypothesis), and the four author tools are separated by explicit use cases (papers, directions, profile, neighbors). There is mild overlap where get_author_context bundles main papers and directions that get_author_papers/get_author_directions return in full, and where get_institution_context's capped author list overlaps get_institution_authors, but the descriptions make the compact-vs-paginated distinction clear.
Names follow a predictable get_<entity>[_<subresource>] pattern throughout (get_paper, get_direction_papers, get_author_neighbors, get_institution_authors). The only deviation is search_lacuna, which breaks the get_ verb style, though as the single entry-point search tool it is still easy to place.
Thirteen tools is well within the ideal band and each one earns its place by covering a distinct entity type in a multi-entity research corpus. The search mega-tool absorbs query-side variation instead of spawning a dozen narrow search endpoints.
Coverage is broad and mostly symmetric: paper, direction, author, venue, institution, resource, and hypothesis all have retrieval paths, and pagination exists for direction papers and institution authors. Minor gaps remain, notably no paginated venue-paper listing (parallel to get_direction_papers) and no explicit citation/reference traversal beyond the 'neighbors' related-papers view.