국내 주식·채권 MCP (Korea Stocks & Bonds)

지분 변동

stake_changes

Read-onlyIdempotent

[국내 주식 + 채권 MCP FinQuest] 지분 변동 — 5% 대량보유 보고(연기금·운용사 등)와 임원·주요주주 소유 보고. 종목을 주면 그 회사 보고 이력(보고자·직위·보유·증감·비율·사유), 없으면 시장 전체에서 최근 N일 늘어난·줄어든 지분을 금액(증감 주식 × 현재 종가) 순으로. '최근 임원이 많이 산 회사', '국민연금이 지분 늘린 회사', '이 회사 대주주 지분 변화' 같은 질문에. 출처 OpenDART.

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": "stake_changes"
  }
}

Input Schema

Name	Required	Description
`days`	No	시장 전체: 최근 며칠 (기본 30)
`kind`	No	생략하면 둘 다
`limit`	No
`stock`	No	종목코드(6자리) 또는 종목명. 예: '005930', '삼성전자'
`holder`	No	보고자 이름 일부, 쉼표로 여러 개 — 특정 주주 추적 (예: '국민연금', '블랙록,뱅가드', '얼라인,KCGI,트러스톤' 행동주의)
`market`	No
`min_mcap`	No	시가총액 하한(억원)
`direction`	No	시장 전체: 늘어남·줄어듦·둘 다(기본)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

addedInput schema / properties / holder

Added value: +{
+  "description": "보고자 이름 일부, 쉼표로 여러 개 — 특정 주주 추적 (예: '국민연금', '블랙록,뱅가드', '얼라인,KCGI,트러스톤' 행동주의)",
+  "type": "string"
+}

AddedNov 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds value beyond those annotations: the data source (OpenDART), the default of 30 days for market mode, the default of both report kinds, and the ranking rule (증감 주식 × 현재 종가).

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 a single dense paragraph, and the core dual-mode behavior comes first. No filler sentences, but it is packed tightly and would read better structured into two lines for the two modes.

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?

For an 8-optional-parameter, no-output-schema read tool, the description covers both modes, defaults, ranking logic, and the returned fields (보고자·직위·보유·증감·비율·사유). An agent has enough to choose the mode and build the call correctly.

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 coverage is 75%, so this dimension needs the description to fill gaps, and it does. It explains that 'stock' selects company-history mode, describes 'holder' as partial-name matching with comma-separated multiple values (including an activism example), and describes market mode's ranking and direction semantics. It doesn't cover 'limit' or 'min_mcap' beyond the schema.

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 names a specific resource (5% 대량보유 보고 and 임원·주요주주 소유 보고 disclosure data from OpenDART) and explicitly splits it into two query modes: company-specific report history when 'stock' is given, and market-wide ranked stake changes otherwise. That is far beyond the title alone and lets an agent distinguish it from siblings like shareholders or governance.

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 provides concrete trigger questions ('최근 임원이 많이 산 회사', '국민연금이 지분 늘린 회사', '이 회사 대주주 지분 변화') that map to the two modes. What's missing is explicit routing guidance to the alternative siblings (e.g. shareholders vs. governance) or any statement of when not to use this tool.

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

All 국내 주식·채권 MCP (Korea Stocks & Bonds) 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?