XBOSS

KISCON 건설업체 공시·행정처분 조회

opendata__kiscon__sanction

공공데이터포털에 개방된 KISCON 건설업체 공시(data.go.kr 15061362)를 조회합니다. 원천은 기간(sDate, eDate)으로만 조회할 수 있어, 서버가 그 기간의 공시를 훑어 사업자등록번호(bizno)가 같은 행을 matches 에 돌려줍니다. 공시에 등록번호가 없는 행은 업체명(corp_name)을 넣었을 때 이름이 같은 것을 fallback_candidates 에 담습니다. matches 가 비어 있으면 그 기간에서 찾지 못한 것이고, 처분이 없다는 확인서는 아닙니다. 별도 연동 없이 사용할 수 있습니다. For an authenticated call, generate and save request_idempotency_key before the first request. Reuse it with the same arguments only to recover that request after a lost response; use a new key for a new execution. Without it, calling again remains a new request. This optional key is not available to anonymous taste calls. Keep any provider-specific idempotency_key unchanged; it is a different field. 호출마다 토큰 1소진 요청 처리 시 XBOSS 작업을 생성하고 처리 결과를 저장합니다. 기관 원본의 조회 여부와 별개로 이 호출은 순수 읽기 전용이 아닙니다. 기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차를 따릅니다.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "bizno": "<bizno>",
      "sDate": "<sDate>",
      "eDate": "<eDate>"
    },
    "name": "opendata__kiscon__sanction"
  }
}

Input Schema

Name	Required	Description
`bizno`	Yes	사업자등록번호 10자리. 조회 기간의 공시 가운데 이 번호의 업체 것만 돌려줍니다.
`eDate`	Yes	공시 기간 종료일 YYYYMMDD. 꼭 보내야 합니다.
`sDate`	Yes	공시 기간 시작일 YYYYMMDD. 꼭 보내야 합니다.
`maxPages`	No	훑을 최대 페이지 수(기본 5, 상한 20).
`corp_name`	No	업체명(선택) - 공시에 등록번호가 없는 업체는 이 이름으로 찾습니다.
`numOfRows`	No	기관 페이지당 행 수(기본 100, 최대 100).
`ncrAreaName`	No	등록 시도 필터(선택).
`ncrAreaDetailName`	No	등록 시군구 필터(선택).
`request_idempotency_key`	No	Optional same-request recovery key for authenticated calls; see the tool description.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, and the description corroborates this by disclosing that each call creates an XBOSS task and stores results, so the call is not purely read-only — no contradiction. It also adds genuinely useful behavior: server-side scanning of a date window, a maxPages-bounded scan, and the critical caveat that an empty `matches` is not proof of no sanction. Points are lost for generic idempotency boilerplate that adds little tool-specific value.

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

Conciseness3/5

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

The Korean opening is well front-loaded and efficient, covering purpose, matching mechanics, and the empty-result caveat in a few sentences. However, the long English idempotency paragraph is generic cross-tool boilerplate (including an irrelevant reference to 'anonymous taste calls'), and the closing sentence about institutional data changes is unrelated to this lookup, diluting an otherwise tight definition.

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?

With no output schema and nine parameters, the description carries real weight and delivers: it names the return fields (`matches`, `fallback_candidates`), explains the empty-result interpretation, and states the per-call token cost. The remaining gap is that a bounded page scan (maxPages, default 5) could silently miss matching rows, which is not warned about.

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?

Schema coverage is 100%, so the schema already documents all nine parameters, making 3 the baseline. The description goes partway beyond it by explaining why bizno is required (the source cannot filter by it), how corp_name feeds `fallback_candidates`, and what empty results mean, but it does not explain the practical effect of maxPages or numOfRows on result completeness.

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 names a concrete verb and dataset (KISCON 건설업체 공시, data.go.kr 15061362), so an agent knows exactly which registry is being queried. It does not explicitly contrast itself with lookalike sanction tools such as opendata__g2b__sanction or opendata__env__waste_sanction, leaving that differentiation to the names alone.

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

Usage Guidelines3/5

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

Usage constraints are implied rather than stated as when-to-use rules: the source only supports date-range queries, so bizno filtering is done server-side, and corp_name is a fallback for rows lacking a registration number. There is no explicit statement of when to pick this tool over a sibling sanction lookup, and no prerequisites or exclusions are listed.

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

All XBOSS 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.

Resources

Need Help?