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.
This server publishes no instructions, or was last inspected before Glama recorded them.
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
} |
| experimental | {} |
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, and novel research hypotheses. For novel ML/AI research ideas, use search_type="hypothesis", then get_hypothesis on promising results. search_type accepts all, cluster/direction, paper, author, institution, venue, or hypothesis/proposal; singular and plural aliases are accepted. Use other sources for biographies, news, and non-research web content. 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. fields optionally restricts and weights lexical fields, for example "title^4,abstract". Supported names are title, abstract, summary, concepts, name, top_names, and venue. 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 | Fetch a Lacuna research direction/cluster. 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 a Lacuna paper by artifact id or paper URL. 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_author_papersA | Fetch one page of an author's papers, ordered from newest to oldest. |
| get_author_directionsA | Fetch one page of an author's named research directions. |
| get_author_contextA | Fetch agent-oriented context for a Lacuna author. 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 | Fetch one ranked page of neighboring/similar Lacuna authors. |
| get_venue_contextA | 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 /venue/... page URL. view selects the response shape:
|
| get_institution_contextA | Fetch agent-oriented context for a Lacuna institution. view selects the response shape:
Use get_institution_authors to page through the complete author list. |
| get_institution_authorsA | 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool targets a distinct resource or action: search, hypothesis, direction, paper, author context/papers/directions/neighbors, venue, and institution. Even related tools like get_direction and get_direction_papers are clearly separated by whether they return metadata or paginated papers. No two tools appear to do the same thing.
All tool names follow a consistent verb_noun pattern: search_lacuna, get_hypothesis, get_direction, get_paper, get_author_papers, get_venue_context, etc. The addition of contextual qualifiers like 'author_papers' vs 'author_context' is predictable and uniform. No mixing of camelCase or inconsistent verb styles.
The 12 tools are well-scoped for a research corpus server, covering search, hypotheses, directions, papers, authors, venues, and institutions without unnecessary proliferation. Each tool serves a distinct need in the research retrieval workflow. This aligns with the expected range of 3-15 tools.
The tool surface covers the full lifecycle of research discovery: search across all entity types, then fetch detailed context, papers, directions, and related entities for each. Author, direction, and institution sub-resources (papers, neighbors, authors) are included, and the flexible search_type parameter fills any gaps. No obvious dead ends or missing operations for a read-only research API.