Skip to main content
Glama

Mdexa

Search datasets

search_datasets
Read-onlyIdempotent

Mdexa is a database of biomedical datasets that agents call over MCP or, with an API key, an HTTP API. Use this first: keywords (q) and filters, every condition in one call. COMPLETENESS: 'Complete: these are ALL N datasets ...' means you hold the full answer: do not repeat the search with other words or filters. FILTERS: several values of ONE parameter are ORed; different parameters are ANDed; a parent domain includes its sub-domains. The tag facets task_format, intended_use, specialty, condition_scope, population, source_type, annotation_depth, expert_involvement, size_tier, data_format, official_split, benchmark_status (specialty = department, condition_scope = ICD-11 chapter); their values come from list_facets (only=), and a wrong value is answered with the allowed ones. Known slugs: slugs=a,b needs no keyword. q: Chinese or English or another language; typos, synonyms and meaning are matched. Each row has answer (license status, commercial_use, derivatives, redistribution, key quote with URL and date), risk_flags, repo_only (true = only a code repository license), card_url, last_verified: enough for license questions. Models: code and weights licenses apart. Registered entries: no conclusion. restricted, conflict, unstated and unverifiable never mean commercial use is allowed. Output fits max_tokens (default 1500); next_cursor gives more. no_match (did_you_mean) means the Mdexa database does not list it: do not retry with other words. related rows are nearby records, NOT matches.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_datasets"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoKeywords or a short description, any language.
langNoen
sortNorelevance
tierNoverified and practical: license concluded with evidence; registered: listed, NOT verified. Default all, verified first.
typeNo
hintsNooff: no return note and the visit is not recorded (the same as the header X-Mdexa-Hints: off). on or absent: default.
limitNo
matchNoall = every word must match.ranked
priorNofalse = pure text relevance.
slugsNoExact slugs (OR); unknown ones come back in unknown_slugs.
cursorNonext_cursor of the previous response.
domainNo
systemNo
explainNoAdd match.fields / match.via to each row.
hostingNo
year_toNo
languageNoBCP 47, e.g. zh, lzh, en.
modalityNo
synonymsNofalse = literal words only.
risk_flagNonone = no flag.
size_tierNo
specialtyNo
year_fromNo
max_tokensNoResponse size cap in estimated tokens; rows are dropped from the end.
populationNo
tag_sourceNodeclared = only tags the authors state or a reviewer confirmed.any
data_formatNo
source_typeNo
task_formatNo
content_typeNo
intended_useNo
license_statusNopermissive = commercial use and redistribution allowed; unreviewed = registered, no conclusion.
official_splitNo
condition_scopeNo
include_derivedNofalse = only stated or inferred tags.
annotation_depthNo
benchmark_statusNo
expert_involvementNo

Output Schema

NameRequiredDescriptionDefault
itemsNo
totalNo
completeNo
no_matchNo
next_cursorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the read-only annotations, the description explains completeness semantics, pagination via next_cursor, max_tokens truncation, no_match handling, and related-row semantics. It also discloses important license interpretation caveats, including that restricted, conflict, unstated, and unverifiable never mean commercial use is allowed.

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?

The description is long but justified by the tool's 38-parameter surface and complex result semantics. It uses capitalized labels and front-loads the core search purpose, though the dense single block and terse fragments like 'Models: code and weights licenses apart' reduce scannability.

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

Completeness4/5

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

For a complex search tool with an output schema and read-only annotations, the description covers the critical operational behaviors: completeness, filter logic, facet sourcing, license caveats, pagination, and no_match handling. It is not fully complete because several parameters remain undocumented, but it gives an agent enough to invoke the tool correctly in most cases.

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

Parameters3/5

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

With 38 parameters and only 39% schema description coverage, the description carries a heavy burden; it does add valuable semantics for q, slugs, domain hierarchy, OR/AND filtering, facet values from list_facets, max_tokens, cursor, and license_status. However, many parameters such as sort, tier, type, hosting, content_type, explain, and include_derived receive little or no explanation, so compensation is partial.

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

Purpose4/5

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

The description states a specific verb and resource: searching a biomedical dataset database using keywords and filters, with 'Use this first' signaling its role as the broad entry point. It distinguishes itself from list_facets in the text but does not explicitly differentiate from siblings such as search_content or find_similar_datasets.

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

Usage Guidelines4/5

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

It gives clear usage direction: use this first, combine all conditions in one call, do not repeat a search after a 'Complete' response, and do not retry after no_match. It also directs the agent to list_facets for valid facet values. The main gap is that it does not compare itself with other search-like siblings.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.