k-dart-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DART_API_KEY | No | OpenDART API authentication key. If not set, the server uses the credentials stored at ~/.k-dart-mcp/credentials.json. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_companyA | 회사명·종목코드로 기업을 검색합니다. 유사 기업 후보와 정확한 DART 고유번호를 확인합니다. |
| search_disclosuresB | 기업별 공시 목록과 원문 링크를 조회합니다. 기본 최근 30일. 페이지 정보를 보존하며 본문을 읽지 않습니다. |
| get_financial_summaryA | 매출·영업이익·순이익·자산·부채·자본의 표준계정을 조회합니다. 누락·모호한 계정은 null. 분기 금액과 누적 금액을 따로 반환합니다. |
| get_full_financial_statementsB | 전체 재무제표 계정과 원문 금액을 조회합니다. offset/limit으로 이어서 조회하세요. |
| compare_financialsA | 최대 5개 기업을 같은 사업연도·보고서·연결/별도 기준으로 조회합니다. 회사별 실패와 누락을 보존합니다. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
The company/disclosure searches are clearly separated by resource, and the summary vs. full-statements split is explicit in the descriptions (standard accounts with nulls vs. all accounts with pagination). The two financial-retrieval tools still share the 'get financials' space, though descriptions disambiguate them well.
All five tools follow a clean verb_noun snake_case pattern (search_company, search_disclosures, get_financial_summary, get_full_financial_statements, compare_financials). No mixed conventions or vague verbs.
Five tools is well within the ideal range, and each one maps to a distinct capability (company lookup, disclosure listing, summary financials, full statements, comparison). Nothing feels redundant or missing at the count level.
The surface covers discovery, disclosure listing, financial summary, full statements, and cross-company comparison, which is solid read coverage for a public disclosure API. A minor gap is the inability to read a disclosure's body text, since search_disclosures explicitly returns only links and page info.