Connect Lacuna Research and your agent gets 13 tools, among them get_author_context, get_author_directions, get_author_neighbors. It answers at https://lacuna.tiptreesystems.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 2 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Search Lacuna's ML research graph for papers, directions, authors, venues, and hypotheses.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_author_context | Fetch agent-oriented context for a Lacuna author. Author profiles describe research output (papers, directions, impact). A free-text `affiliation` field may be present but can be incomplete or outdated and may not represent current employme Inputs: author_id_or_url, view, include_neighbors |
get_author_directions | Fetch one page of an author's named research directions. Inputs: author_id_or_url, limit, offset |
get_author_neighbors | Fetch one ranked page of neighboring/similar Lacuna authors. Inputs: author_id_or_url, limit, offset |
get_author_papers | Fetch one page of an author's papers, ordered from newest to oldest. Inputs: author_id_or_url, limit, offset |
get_direction | Fetch a Lacuna research direction/cluster. Use a numeric cluster ID (for example 25005) or a direction URL ending in that number. view selects the response shape (`context` typically contains the fields `full` provides plus the agent-orient Inputs: cluster_id_or_url, view |
get_direction_papers | Fetch paginated papers associated with a Lacuna research direction/cluster. view selects the per-paper shape: - "compact" (default, recommended): citation-ready rows (id, url, title, year, venue, a few authors, abstract snippet). Drops the Inputs: cluster_id_or_url, page, limit, view |
get_hypothesis | 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: - "context" (default, recommended): compact single-fetch proposal context Inputs: hypothesis_id_or_url, view |
get_institution_authors | Fetch one page of authors affiliated with a Lacuna institution. Results are ordered by paper count. Use authors_total, authors_returned, authors_offset, and authors_truncated to page through the complete list. Inputs: institution_key_or_url, limit, offset |
get_institution_context | Fetch agent-oriented context for a Lacuna institution. view selects the response shape: - "context" (default, recommended): compact institution context — capped top authors with the duplicated institution block dropped server-side. - "full" Inputs: institution_key_or_url, view |
get_paper | Fetch a Lacuna paper by artifact id or paper URL. 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 Inputs: artifact_id_or_url, view, figure_limit, include_resources |
get_resource | 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/<slug>/art_...). The response includes the external url, a summary, Inputs: resource_id_or_url |
get_venue_context | Fetch agent-oriented context for a Lacuna venue, optionally scoped to a year. 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 /v Inputs: venue_key_or_url, year, view |
search_lacuna | 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). For novel ML/AI research ideas Inputs: query, search_type, limit, offset, author_id_or_url, date_from |
Every block below points at https://lacuna.tiptreesystems.com/api/mcp. Pick your client and copy.
claude mcp add --transport http lacuna-research https://lacuna.tiptreesystems.com/api/mcp
{
"mcpServers": {
"lacuna-research": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://lacuna.tiptreesystems.com/api/mcp"]
}
}
}{
"mcpServers": {
"lacuna-research": {
"url": "https://lacuna.tiptreesystems.com/api/mcp"
}
}
}{
"servers": {
"lacuna-research": {
"type": "http",
"url": "https://lacuna.tiptreesystems.com/api/mcp"
}
}
}{
"context_servers": {
"lacuna-research": {
"url": "https://lacuna.tiptreesystems.com/api/mcp"
}
}
}{
"mcpServers": {
"lacuna-research": {
"serverUrl": "https://lacuna.tiptreesystems.com/api/mcp"
}
}
}{
"mcpServers": {
"lacuna-research": {
"url": "https://lacuna.tiptreesystems.com/api/mcp"
}
}
}name: Lacuna Research
version: 0.0.1
schema: v1
mcpServers:
- name: Lacuna Research
type: streamable-http
url: https://lacuna.tiptreesystems.com/api/mcp{
"mcpServers": {
"lacuna-research": {
"httpUrl": "https://lacuna.tiptreesystems.com/api/mcp"
}
}
}{
"mcpServers": {
"lacuna-research": {
"type": "http",
"url": "https://lacuna.tiptreesystems.com/api/mcp"
}
}
}{
"mcpServers": {
"lacuna-research": {
"url": "https://lacuna.tiptreesystems.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Flacuna.tiptreesystems.com%2Fapi%2Fmcp&type=streamable_http&id=lacuna-research&name=Lacuna%20Research
It answered our last check on 24 October 2026 in 420 ms. Over 6 checks since 11 September 2026 it answered 2. Status here comes from Neuronto's own probes, not from the publisher.
13, as returned by the server's own tools/list on 25 October 2026: get_author_context, get_author_directions, get_author_neighbors, get_author_papers, get_direction, get_direction_papers, get_hypothesis, get_institution_authors, and 5 more.
It answered our last check on 24 October 2026 in 420 ms. Over 6 checks since 11 September 2026 it answered 2.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://lacuna.tiptreesystems.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.tiptreesystems. Endpoint host: lacuna.tiptreesystems.com. ARD identifier: urn:air:io.github.tiptreesystems:mcp:lacuna-research-mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.