Skip to main content
Glama
hvj78

MEK-MCP

by hvj78

mek_advanced_search

Combine up to five field conditions with AND, OR, NOT to search the MEK catalogue across 24 metadata fields, including author, subject, title, language, and more.

Instructions

Advanced (fielded) search in the MEK catalogue with up to 5 conditions combined via AND / OR / NOT over 24 metadata fields.

Available fields: main_title, subtitle, collection_title, part_title, parallel_title, original_title, series, author, author_role, corporate_author, contributor, contributor_role, publisher, subject, geographic_subject, period_subject, document_type, format, language, original_language, printed_source, rights_owner, rights_note, creative_commons.

Typical patterns:

  • Works BY a person: field=author, value='Petőfi Sándor'.

  • Works ABOUT a person: field=subject, value='Petőfi Sándor'.

  • Person in any role: run separate author / subject / contributor searches (OR across different fields of different records is best done client-side by merging results).

  • Exclusions: add a condition with operator='not' (e.g. document_type='útikönyv' with 'not' to drop travel guides).

  • Language filter: field=language, value='magyar' / 'angol' / ...

  • Values are matched against controlled vocabulary; use mek_browse_index to discover exact term forms, and * for prefixes.

Returns: {total, offset, hits: [{mek_id, url, authors, title, date_added}], has_more, accent_fallback_used}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
offsetNoResult offset for paging. The server returns up to 100 hits per page; pass 100, 200, ... for further pages.
conditionsYes1 to 5 search conditions. Each condition has a field, a value and an operator ('and'/'or'/'not') that links it to the previous condition. Example (Hungarian-language AI works excluding programming textbooks): [{'field':'subject','value':'mesterséges intelligencia'}, {'field':'language','value':'magyar','operator':'and'}, {'field':'subject','value':'programozás','operator':'not'}]
accent_insensitiveNoIf true, accented and unaccented letter forms are treated as equal (MEK 'ékezet nélküli keresés'). Useful when the exact accented form of a name/term is unknown.
auto_accent_fallbackNoIf true (default) and the search yields 0 hits, the search is automatically retried with accent-insensitive matching; the response then contains accent_fallback_used=true so you can tell the user the hit set was widened this way.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

No annotations provided, so description carries full burden. It discloses the return structure ({total, offset, hits, has_more, accent_fallback_used}), accent fallback behavior, and controlled vocabulary matching. Missing explicit rate limits or error handling, but overall transparent.

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

Conciseness5/5

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

The description is concise and well-structured: first sentence states purpose, followed by field list, typical patterns, and return structure. No unnecessary words, and key information is front-loaded.

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?

Given the complexity (4 parameters, nested conditions, output schema exists), the description is highly complete. It covers field list, patterns, controlled vocabulary, accent behavior, and return shape. Only minor details (like pagination limit) are in schema but not repeated, which is acceptable.

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

Parameters4/5

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

Schema description coverage is 100%, so baseline 3. The description adds value beyond schema by providing examples (e.g., full JSON for conditions), explaining field usage (e.g., author vs. subject), and clarifying operator behavior. This significantly aids understanding.

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?

The description clearly states it's an 'Advanced (fielded) search' with up to 5 conditions combined via AND/OR/NOT over 24 metadata fields. It lists available fields and provides typical patterns, effectively distinguishing it from siblings like mek_simple_search and mek_fulltext_search.

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?

The description gives typical patterns (e.g., 'Works BY a person', 'Works ABOUT a person', exclusions, language filter) and suggests using mek_browse_index for controlled vocabulary. It does not explicitly state when not to use this tool, but the patterns provide clear context for usage.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hvj78/MEK-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server