Skip to main content
Glama
Sign In
meritz-securities

meritz-mcp

Official
by meritz-securities
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

메리츠 국내 시세(주식·지수)

meritz_market
Read-onlyIdempotent

Query Korean domestic stock and index quotes, candles, investor flows, order books, and trades by selecting an api_type and passing params; use api_type='describe' to retrieve parameter guidance.

Instructions

메리츠 Open API — 국내 시세(주식·지수) (13건). api_type 으로 호출할 API 를 고르고 params 에 파라미터를 넣습니다. api_type='describe' 로 부르면 파라미터 설명을 돌려줍니다. ★ 국내 일봉(market_candles_days)은 기본이 KRX 정규장 종가입니다 (mrkt_div_code 를 생략하면 'TJ').

market_candles_days GET 시세추이 조회(일봉) market_candles_minutes GET 시세추이 조회(분봉) market_index_candles_days GET 국내지수 시세추이 조회 market_index_candles_minutes GET 국내지수 시세추이 조회 (분봉) market_index_prices GET 국내지수 현재가 조회 market_investors GET 종목별 투자자매매동향 market_investors_detail GET 종목별 투자자매매동향 상세 market_orderbook GET 호가 조회 market_orderbook_after GET 시간외 단일가 호가 조회 market_prices GET 현재가 조회 market_prices_after GET 시간외 단일가 조회 market_trades_minutes GET 체결추이 조회(분) market_trades_ticks GET 체결추이 조회(틱)

Input Schema

NameRequiredDescriptionDefault
paramsNo
accountNo
api_typeYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.12
    • addedInput schema / properties / account
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  2. First observedv0.3.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: daily candles default to KRX regular-session close when mrkt_div_code is omitted ('TJ'), which materially changes returned data. It is silent on rate limits, auth handling, and market-hours behavior, keeping it below a 5.

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?

Front-loaded with the operating model (api_type + params + describe), then the endpoint table, with the important default flagged by a star. The 13-line list is long but each line earns its place as a dispatchable value; a short example params payload would have displaced less valuable text than it added.

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 13 multiplexed endpoints, an output schema present, and full safety annotations, the description covers enough for correct invocation: dispatch key, argument channel, introspection path, and one critical default. The remaining gap is that no single worked example of params is given and the account parameter is unexplained.

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 description coverage is 0%, so the description carries the burden, and it partly compensates by naming the api_type values and the describe mechanism for per-endpoint parameters. However, the actual contents of the params object are never illustrated and the 'account' parameter is never mentioned at all, leaving the agent to make a discovery call for every endpoint.

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?

States a specific verb and resource (domestic quotes for stocks and indices via the Meritz Open API) and enumerates the 13 underlying endpoints with their HTTP methods, so an agent knows exactly what surface it is calling. The explicit '국내' scoping also separates it from the sibling meritz_overseas_market.

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?

Tells the agent to pick a sub-API via api_type and pass arguments in params, and offers the api_type='describe' escape hatch for parameter discovery. It does not state when to prefer this over e.g. meritz_reference or meritz_info for static data, but the domestic/quote scope makes the boundary mostly self-evident.

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

Deploy Server

Other Tools