Lacuna Research MCP

Search Lacuna

search_lacuna

Read-onlyIdempotent

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, 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 `url`, a Lacuna `context_url`, and
`linked_paper_count`; call get_resource on its id to list the linked papers
(with their relationship to the resource), then get_paper on those papers
for reported results and numbers. Resource search does not support
date_from/date_to, venue, year sorting, or semantic ranking.

ranking_profile accepts:
- default / lexical (default): production ranking; relevance-sorted paper
  searches combine lexical and semantic retrieval when fields is unset.
- semantic: conceptual paper retrieval; supported for paper and all.
- bm25_title_abstract / bm25: lexical paper matching over those fields.

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.

Input Schema

Name	Required	Default
`sort`	No	relevance
`limit`	No
`query`	Yes
`venue`	No
`fields`	No
`offset`	No
`date_to`	No
`provider`	No
`date_from`	No
`search_type`	No	all
`resource_kind`	No
`ranking_profile`	No
`author_id_or_url`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 13, 2026

TDQS

A4.9/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, idempotent, openWorld, non-destructive), and the description layers on real behavioral constraints: resource search ignores date_from/date_to, venue, year sorting and semantic ranking; semantic ranking cannot use year sorting; filters must pair with search_type resource/all and then only resources are returned. These are non-obvious caveats an agent could not infer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well front-loaded (purpose, then follow-up routing, then per-parameter reference) and organized into digestible blocks. It is dense and reference-manual length for a 13-parameter tool, with mild redundancy (the resource filter restriction is restated after the resource support list), but nearly every sentence is load-bearing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, and the description still adds useful result-shape context (external url, context_url, linked_paper_count). Across 13 parameters with zero schema descriptions, the description leaves no mode, filter interaction, or format ambiguity that would cause a misinvocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there are no enums, so the description carries the full burden — and it does: it enumerates search_type, ranking_profile, sort, resource_kind, provider values, date bound formats (YYYY / YYYY-MM / YYYY-MM-DD, inclusive), the fields weighting syntax with its 0 < weight <= 100 rule, and the author_id_or_url constraint. Only limit/offset are left undocumented, which are conventional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource ('Search Lacuna's ML/AI corpus') and enumerates exactly what is retrievable (papers, directions, authors, venues, institutions, hypotheses, resources). It distinguishes itself from siblings by routing follow-up work to get_hypothesis, get_paper, and get_resource by name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use branches: search_type="hypothesis" plus get_hypothesis for novel ideas, "paper" plus get_paper for literature, resource_kind="dataset" for benchmarks, and 'other sources' for biographies/news. It also states conditions that select each mode (e.g. filters require search_type resource or all).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Lacuna Research MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.