Skip to main content
Glama

MyFSS

by kr.eocpa

회계·공시 자료 전문검색

search_documents
Read-onlyIdempotent

MyFSS MCP의 search_documents 도구는 금융감독원(FSS)·금융위원회(FSC) 회계·공시 자료를 전문검색합니다.

[Purpose]

  • What 감독당국 checks — 심사·감리 지적사례·감독지침·모범사례 등 게시판 11종.

  • Filters alone (no query) sweep a topic.

[Usage]

  1. "전환사채 콜옵션 관련 감독원 자료" → query="전환사채 콜옵션"

  2. "작년 감리 지적사례 전부" → board="sanction_case", date_from="2025-01-01", date_to="2025-12-31"

  3. "내부회계관리제도 주제로 20건" → topics=["내부회계관리제도"], limit=20

[Response]

  • { total, showing, offset, note, results:[{ntt_id, date, board, source, title, nature, topics, depts, summary, url, snippet?}] }

  • total = 전체 건수, showing = 이번 페이지 — paginate with offset.

  • source: "fss"=금융감독원, "fsc"=금융위원회.

  • snippet marks matches with [ … ]; only when a query matched.

[Rules]

  • board is asymmetric: param = English key, response = 한글 라벨 — never feed it back.

  • topics·depts are joined strings (", " / " / "), not arrays — split first.

  • ≥3-char tokens → FTS (AND, rank); 1~2-char → LIKE. No query → 게시일 DESC, no snippet.

  • Corpus = 2010 onward (absent = 미수록); quote body via get_document, not summary·snippet.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
deptNo담당부서명 부분일치 (예: '회계감리')
boardNo게시판 필터
limitNo최대 결과 수 (기본 15)
queryNo검색 키워드 (공백 구분, 예: '전환사채 콜옵션')
natureNo문서 성격 필터
offsetNo페이지네이션 오프셋
sourceNo발행기관 필터 (fss=금융감독원, fsc=금융위원회)
topicsNo주제 태그 필터 (하나라도 일치, list_tags의 topics 값)
date_toNoYYYY-MM-DD 이전
date_fromNoYYYY-MM-DD 이후

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

The description goes far beyond annotations: it discloses the board key/label asymmetry, that topics/depts are joined strings requiring split, the FTS-vs-LIKE token length rule, no-query descending date ordering, corpus coverage from 2010, and snippet-only-on-match behavior. This is rich, non-obvious behavioral detail.

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 long but well-organized into Purpose, Usage, Response, and Rules sections. Every line carries necessary information for a 10-parameter search tool, and front-loading the purpose makes it scannable despite the density.

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?

With no output schema, the description fully documents the response shape, pagination via total/offset, source labels, snippet conditions, and the get_document fallback for body content. It also addresses search semantics, board asymmetry, and corpus boundaries, leaving no significant calling gap.

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?

Although schema coverage is 100%, the description adds substantial meaning: query-to-parameter examples, the board English-key/한글-label mismatch, filter-only sweeping, and the no-query behavior. It clarifies how to combine parameters effectively, which the schema alone does not convey.

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 clearly states the tool performs full-text search over FSS/FSC accounting and disclosure materials, and it enumerates the board categories and example queries. However, it never explicitly distinguishes itself from sibling tools like list_recent or list_tags; the differentiation is only implied by the term '전문검색' and a later rule mentioning get_document.

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 [Usage] section provides three concrete natural-language-to-parameter mappings and a rule directing users to get_document for quote bodies. It lacks explicit when-not-to-use guidance for the sibling list tools, though the examples give clear context for typical search scenarios.

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

All MyFSS toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation4/5

Each tool has a distinct role: search_documents handles query-based search with pagination, list_recent is the no-query recent feed, list_tags supplies filter vocabulary, get_document retrieves full text, and get_usage_stats is server telemetry. The only mild overlap is between list_recent and a query-less search_documents, but the descriptions explicitly separate quick skim from fuller search.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: get_document, get_usage_stats, list_recent, list_tags, search_documents. The naming is predictable and makes the purpose of each tool immediately clear.

Tool Count5/5

Five tools is well-scoped for a read-only regulatory document search and retrieval server. The set covers discovery, search, vocabulary validation, full-text access, and usage monitoring without redundant or excessive tools.

Completeness5/5

The core workflow is fully covered: discover documents via search or recent listing, validate filter values via list_tags, and retrieve full text with pagination via get_document. Since this is a read-only corpus, the absence of create/update/delete tools is appropriate rather than a gap.

Resources