HOLD! Korea Stock Ownership & Insider Trades
REMOTE · WHOHOLD.COM
Who owns Korean listed stocks, from DART filings: 5% holders, insiders, stake changes, average cost.
Available components
Last scanned (13 hours ago)
Scores higher than 10% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability0
- Transport check failed: declared streamable-http, but the endpoint returned HTTP 402. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability0
- Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
- Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
- Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified
Unverified: 5 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
Checks we ran (5)
- TLS certificate
- HTTPS
- HSTS header
- DNSSEC
- Transport
Checks we could not complete (6)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Authorization in Endpoint SecurityAuthorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- Schema quality in Schema Quality & AI Usability (scores 0 for this)Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
- Tool coverage in Tool Coverage (scores 0 for this)Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- Tool safety in Tool Safety (scores 0 for this)Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- Capabilities in Capabilities (scores 0 for this)Capabilities not yet verified: we couldn't read the endpoint's capabilities.
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Nov 26 −49
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: 0.23 → unverified ▼ security
- Authorization: partial → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 16 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Nov 26 +1
- Tool “get_holders” rewrote its description, which is the text the model reads security
- Tool “get_avg_cost” rewrote its description, which is the text the model reads security
- Schema quality: 4401 → 5717 ▼ functional
- New tool “get_holder_summary” functional
- New tool “get_institution_flows” functional
- “get_holders” added an optional parameter “tickers” cosmetic
- “get_holders” made “ticker” optional cosmetic
- 10 Nov 26 0
- Tool “get_holder_history” rewrote its description, which is the text the model reads security
- Tool “get_portfolio” rewrote its description, which is the text the model reads security
- Stability: unverified → 0.03 ▲ functional
- “get_holder_history” added an optional parameter “offset” cosmetic
- “get_holder_history” reworded the description of “limit” cosmetic
- 9 Nov 26 71
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://whohold.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=*.whohold.com | CN=YR1,O=Let's Encrypt,C=US | 4 Nov 2026 | 2 Feb 2027 | RSA 2048 | SHA256-RSA | 622e63f0734e4f4523e433ef5e4dfb617e7 |
| SANs: *.whohold.com, whohold.com | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of whohold.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| whohold.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Inconclusive
We could not reach the endpoint well enough to judge its authorisation posture.
| Result | Inconclusive |
|---|---|
| HTTP status | 402 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://whohold.com/mcp | HTTP error | 402 | |
| http (plaintext) | http://whohold.com/mcp | HTTPS enforced | 308 | https://whohold.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
get_avg_cost ~607
Average purchase price (KRW) per holder for one stock. Uses the acquisition prices in the detailed-change section of original 5% large-holding reports: buys add to the weighted average, sells only reduce the quantity (moving average), and stock splits and reverse splits are adjusted. Insider reports carry no price and are not used. holder (part of a filer name) limits to that holder; otherwise all holders with price data. Each row has avg_cost, held_shares (current holding), priced_shares (bought shares that carry a price), coverage_pct, buys, first_trade and last_trade. basis reported means at least half of the current holding has prices; partial means only some (see coverage_pct); unavailable means no prices (the National Pension Service and foreign funds file simplified reports that legally omit prices). When partial, do not state 'average cost is X won' as fact. close is the latest Friday close (close_date) and return_pct is close / avg_cost − 1 in percent: the paper return on the priced buys, ignoring dividends and gains already taken on sells; null when avg_cost is null. Treat it as approximate when basis is partial. 한 종목의 보유자별 평균 매입단가(원). 5% 대량보유 보고서 원문의 세부변동내역에 적힌 취득 단가로 매수는 가중평균에 더하고 매도는 수량만 줄이는 이동평균을 내며, 액면분할·병합은 보정한다. 임원·주요주주 보고에는 단가가 없어 쓰지 않는다. holder(보고자명 일부)를 주면 그 보유자만, 없으면 단가가 있는 보유자 전부. 행마다 avg_cost, held_shares(현재 보유), priced_shares(단가가 붙은 매수 주식), coverage_pct, buys, first_trade·last_trade를 준다. basis가 reported면 현재 보유분의 절반 이상에 단가가 있고, partial이면 일부만(coverage_pct 참고), unavailable이면 단가가 없다(국민연금·외국계 약식 보고는 법적으로 단가 생략). partial일 때 '평단 X원'이라고 단정하지 말 것. close는 최근 금요일 종가(close_date), return_pct는 close / avg_cost − 1(%)로 단가가 붙은 매수분의 평가 수익률이다. 배당과 매도로 이미 낸 손익은 빠지고, avg_cost가 null이면 null이다. basis가 partial이면 대략적인 값으로 다룬다.
| Name | Type | Req | Description |
|---|---|---|---|
| holder | string | – | Part of the filer's name. 보고자명 일부 |
| ticker | string | yes | Ticker code or exact Korean company name; resolve English names with search_symbol first. 종목코드 또는 정확한 한글 종목명 |
No output schema declared.
No examples provided.
get_filing ~508
Details of one filing. Pass a source_url (DART address) from another tool's result or the 14-digit receipt number (rcept_no). reports are the filing's holder rows (stake, change, filing date); members are, for 5% reports, shares and stake per filer and special-relationship party; trades are the detailed changes (actual trade date, acquisition/disposal method, share class, quantity before and after, price). members and trades exist only for 5% large-holding reports whose original was fetched. Use it to see which trades changed a stake and whether it was a purchase or a debt-to-equity swap. It covers one filing only; to list a stock's filings use get_holder_history, and for filings across stocks use get_recent_changes. A filing that is not stored (only the last 2 years of 5% and insider reports are) returns an error. 공시 한 건의 세부 내역. 다른 도구 결과의 source_url(DART 주소)이나 14자리 접수번호(rcept_no)를 넣는다. reports는 그 공시의 보유자 행(지분율, 변동, 공시일), members는 5% 보고의 보고자·특별관계자별 보유 주식수와 지분율, trades는 세부변동내역(실제 거래일, 취득·처분 방법, 주식 종류, 변동 전후 수량, 단가). members·trades는 원문을 받은 5% 대량보유 보고에만 있다. 어떤 거래로 지분이 바뀌었는지, 매수인지 출자전환인지 확인할 때 쓴다. 공시 한 건만 보므로 한 종목의 공시 목록은 get_holder_history, 여러 종목의 공시는 get_recent_changes를 쓴다. 저장되지 않은 공시(최근 2년 5%·임원 보고만 있다)는 오류를 준다.
| Name | Type | Req | Description |
|---|---|---|---|
| filing | string | yes | A DART URL from source_url (e.g. https://dart.fss.or.kr/dsaf001/main.do?rcpNo=20251105000123) or the 14-digit rcept_no alone; the first 14-digit number in the string is used. source_url(DART 주소) 또는 1… |
No output schema declared.
No examples provided.
get_holder_history ~720
Full history of stake-change filings for one stock (newest first; 5% large-holding reports and insider reports of 1% and above). ticker is required and there is no date limit, so use it for 'when and how did this company's ownership change'. total is the number of matching filings; results come in pages of limit (default 50, up to 200), so when next_offset is present call again with offset=next_offset for older ones, or narrow with from/to. To scan the last few days across many stocks, use get_recent_changes. holder (part of a filer name) limits to that filer. change_type is new/listing/increase/decrease/exit/unchanged; listing is the first filing at IPO, not a purchase. non_trade true means not a market trade (debt-to-equity swap in rehabilitation, capital reduction, collateral, change in special-relationship parties). For insider reports, new may mean 'first report as a major shareholder'. trade_date is the actual change date (only for reports whose original was fetched); trade_price is the average acquisition price in that report. For per-trade details of one filing, pass its source_url to get_filing. 한 종목의 지분 변동 공시 전체 이력(최신순, 대량보유 보고와 1% 이상 임원·주요주주 보고). ticker가 필수이고 기간 제한이 없어 '이 회사 지분이 언제 어떻게 바뀌었나'에 쓴다. total은 조건에 맞는 공시 전체 건수이고 limit(기본 50, 최대 200)씩 나눠 주므로, next_offset이 있으면 offset=next_offset으로 다시 불러 더 오래된 공시를 받거나 from·to로 좁힌다. 여러 종목에 걸쳐 최근 며칠 새 공시를 훑으려면 get_recent_changes를 쓴다. holder로 보고자명 일부를 주면 그 보고자만. change_type은 new/listing/increase/decrease/exit/unchanged. listing은 상장으로 처음 공시한 것이라 매수가 아니다. non_trade가 true면 회생 출자전환, 감자, 담보, 특별관계 변동처럼 시장 매매가 아니다. insider 보고의 new는 '주요주주로서 첫 보고'일 수 있다. trade_date는 실제 변동일(원문을 받은 보고만), trade_price는 그 보고의 취득 단가 평균. 한 보고의 거래별 세부 내역은 source_url을 get_filing에 넘긴다.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_id | number | – | entity_id from search_holder; when given, filters by this holder instead of holder. search_holder의 entity_id. 주면 holder 대신 이 보유자만 |
| from | string | – | YYYY-MM-DD |
| holder | string | – | Part of the filer's name. 보고자명 일부 |
| limit | number | – | Default 50, up to 200. 기본 50, 최대 200 |
| offset | number | – | Skip this many newest filings to page through older ones; use next_offset from the previous result. 앞선 결과의 next_offset |
| ticker | string | yes | Ticker code or exact Korean company name; resolve English names with search_symbol first. 종목코드 또는 정확한 한글 종목명 |
| to | string | – | YYYY-MM-DD |
No output schema declared.
No examples provided.
get_holder_summary ~534
What one holder did over the last N days (default 30): how many stocks it increased and decreased, the total bought and sold in KRW, the net amount, and the largest moves. Default holder is the National Pension Service, so use it for 'what did NPS buy and sell this month'. With entity_id (from search_holder) the holder's related entities are merged as on the website. Market trades only: listing and non_trade changes are left out, and when a 5% report and insider reports cover the same change it is counted once. amount is reported shares × price (the filing's price, else that day's close), positive for increases and negative for decreases; it can be null when no price is known. One 5% report can carry several months of trades and is counted on its filing date. For every filing row use get_recent_changes. 한 보유자가 최근 N일(기본 30일) 동안 한 일: 늘린 종목 수와 줄인 종목 수, 매수·매도 금액 합계(원), 순매수, 큰 변동 목록. 기본 보유자는 국민연금이라 '국민연금이 이번 달 뭘 사고팔았나'에 쓴다. entity_id(search_holder 결과)를 주면 웹사이트처럼 같은 기관의 관련 법인을 합친다. 시장 매매만 센다: listing과 non_trade는 빠지고, 같은 변동을 5% 보고와 임원 보고가 함께 담으면 한 번만 센다. amount는 공시된 주식수 × 단가(공시 단가, 없으면 그날 종가)이고 늘린 쪽은 양수, 줄인 쪽은 음수다. 가격을 모르면 null일 수 있다. 5% 보고 한 건이 여러 달치 거래를 담을 수 있고 공시일에 센다. 공시 행 전체는 get_recent_changes를 쓴다.
| Name | Type | Req | Description |
|---|---|---|---|
| days | number | – | Look-back window by filing date. Default 30, up to 730. 공시일 기준 기간(일). 기본 30, 최대 730 |
| entity_id | number | – | entity_id from search_holder. search_holder의 entity_id |
| holder | string | – | Part of the filer's name, default '국민연금' (National Pension Service). 보고자명 일부, 기본 '국민연금' |
| limit | number | – | Moves listed per side, default 10. 쪽마다 보여 줄 변동 수, 기본 10 |
No output schema declared.
No examples provided.
get_holders ~649
Current major holders of one stock and their stakes, from each holder's latest filing. Use it for 'who owns this company now'; pass tickers to compare up to 10 stocks in one call. For how stakes changed over time use get_holder_history; for everything one holder owns use get_portfolio. Each row in holders has a source field: major (5% large-holding report total), member (per-person or per-company breakdown inside a 5% report) or insider (executive/major-shareholder report, incl. 10%+ shareholders, 1% and above only). groups gives each multi-member 5% group (e.g. the largest shareholder and its special-relationship parties) with the combined stake and member_list (holder, entity_id, ratio_pct), so use it for 'how much does the controlling family own in total'; indirect_holders lists stakes held through other listed companies, with the paths. Every row has as_of (filing date) and source_url (the original filing). Holders with no report in the last 2 years are missing, and there are no foreign or retail totals. An unknown ticker returns an error with search_symbol candidates. 한 종목의 현재 주요 보유자와 지분율(보유자별 최신 공시 기준). '지금 이 회사 주인이 누구인가'에 쓰고, tickers로 최대 10종목을 한 번에 비교한다. 시점별 변동은 get_holder_history, 한 보유자의 전체 보유는 get_portfolio를 쓴다. holders의 각 행에 source 필드가 있다: major(5% 대량보유 보고 합계), member(5% 보고 안의 사람·회사별 내역), insider(임원·주요주주 보고, 10% 이상 주주 포함, 1% 이상만). groups는 여러 명이 함께 낸 5% 보고(예: 최대주주와 특별관계자)의 합계 지분율과 구성원 member_list(holder, entity_id, ratio_pct)라 '최대주주 일가가 모두 합쳐 몇 %인가'에 쓴다, indirect_holders는 다른 상장사를 거친 간접 지분과 그 경로. 모든 행에 as_of(공시일)와 source_url(공시 원문). 최근 2년 안에 보고가 없는 보유자는 빠지고 외국인·소액주주 합계도 없다. 없는 종목이면 search_symbol 후보와 함께 오류를 준다.
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | – | Ticker code or exact Korean company name; resolve English names with search_symbol first. 종목코드 또는 정확한 한글 종목명 |
| tickers | array | – | Up to 10 tickers or exact Korean names to compare in one call; each result is shortened to the top 10 holders and groups, without indirect_holders. 한 번에 비교할 종목 최대 10개. 종목마다 상위 보유자 10명과 groups만 주고 간접… |
No output schema declared.
No examples provided.
get_institution_flows ~456
Institutional net buying and selling across all stocks over the last N days (default 7): by_stock lists the stocks with the largest net buys and net sells by pension funds, foreign and domestic asset managers and financial firms, with the institutions behind each; by_holder lists the most active institutions with their total bought, sold and net. Use it for 'what did institutions buy this week'. Only 5% large-holding reports and 1%+ insider reports, so this is not exchange-wide institutional flow; individuals, listing and non_trade changes are left out. Amounts are in KRW, estimated from reported shares × price. One 5% report can carry several months of trades and is counted on its filing date, so say 'filed this week', not 'bought this week'. For one holder in detail use get_holder_summary. 최근 N일(기본 7일) 전 종목의 기관 순매수·순매도. by_stock은 연기금·외국계·국내 운용사·금융사의 순매수·순매도가 큰 종목과 그 기관들, by_holder는 가장 많이 움직인 기관과 매수·매도·순매수 합계. '이번 주 기관이 뭘 샀나'에 쓴다. 5% 대량보유 보고와 1% 이상 임원 보고만 보므로 거래소 전체 기관 수급이 아니다. 개인, listing, non_trade는 빠진다. 금액은 원이며 공시된 주식수 × 단가로 추정한다. 5% 보고 한 건이 여러 달치 거래를 담을 수 있고 공시일에 세므로 '이번 주에 샀다'가 아니라 '이번 주 공시'로 말한다. 한 보유자를 자세히 보려면 get_holder_summary를 쓴다.
| Name | Type | Req | Description |
|---|---|---|---|
| days | number | – | Look-back window by filing date. Default 7, up to 90. 공시일 기준 기간(일). 기본 7, 최대 90 |
| limit | number | – | Rows per list, default 10. 목록마다 행 수, 기본 10 |
No output schema declared.
No examples provided.
get_portfolio ~514
Stocks held by a holder (default: the National Pension Service), with stakes, highest first. Only stocks with a 5% large-holding report or a 1%+ insider report. With entity_id (from search_holder) you get one person's or one company's holdings only. Searching by holder (part of a name) may mix in other holders with the same name and unverified reports, so check each row's entity_id. value is reported shares × the latest Friday close (KRW); total_value is their sum. If total exceeds shown, raise limit to get more. No match gives empty holdings and matched_holders; try search_holder to check the name. To see who holds one stock use get_holders; for one holder's recent trades use get_recent_changes with entity_id. 보유자(기본 국민연금)가 보유한 종목 목록과 지분율, 지분율 높은 순. 5% 대량보유 보고 또는 1% 이상 임원·주요주주 보고가 있는 종목만. entity_id(search_holder 결과)를 주면 그 한 사람·한 회사의 보유만 나온다. holder(이름 일부)로 찾으면 같은 이름의 다른 보유자와 미확인 보고가 섞일 수 있으니 행의 entity_id를 본다. value는 공시된 주식수 × 최근 금요일 종가(원), total_value는 그 합계. total이 shown보다 크면 limit을 올려 더 받을 수 있다. 맞는 보유자가 없으면 holdings와 matched_holders가 비니 search_holder로 이름을 확인한다. 한 종목의 보유자는 get_holders, 한 보유자의 최근 매매는 get_recent_changes에 entity_id를 준다.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_id | number | – | entity_id from search_holder. search_holder의 entity_id |
| holder | string | – | Part of the filer's name, default '국민연금' (National Pension Service). 보고자명 일부, 기본 '국민연금' |
| include_indirect | boolean | – | true adds indirect stakes held through listed companies: per-stock total_pct and the paths. true면 상장사를 거친 간접 지분까지 합친 종목별 합계(total_pct)와 경로를 준다 |
| limit | number | – | Default 50. 기본 50 |
| min_ratio | number | – | Minimum stake in percent. 최소 지분율(%) |
No output schema declared.
No examples provided.
get_recent_changes ~611
Feed of stake-change filings posted in the last N days (default 7), newest first. Use it across stocks for 'who bought and sold this week', or with entity_id and a large days (up to 730, the stored 2 years) for one holder's filings across all stocks. Insider reports below 1% are left out. ticker limits to one stock; holder or entity_id limits to one holder. For one stock's full history with no date limit, use get_holder_history. Default 50 rows, adjustable with limit. Rows with change listing or non_trade true are not market trades and must be excluded from buy/sell totals. kind is how a 5% filing's new or increased stake arose: buy, placement (rights issue or convertible bond), control (takeover), non_trade, unknown. 최근 N일(기본 7일) 동안 올라온 지분 변동 공시 피드(최신순). 여러 종목을 가로질러 '이번 주 누가 사고팔았나'를 볼 때 쓰고, entity_id와 큰 days(최대 730, 저장된 2년)를 주면 한 보유자의 전 종목 공시 이력이 된다. 1% 미만 임원 보고는 빠진다. ticker를 주면 그 종목만, holder·entity_id를 주면 그 보유자만 거른다. 기간 제한 없이 한 종목의 전체 이력이 필요하면 get_holder_history를 쓴다. 기본 50건이며 limit으로 조절. change가 listing이거나 non_trade가 true인 행은 시장 매수·매도가 아니므로 매매 합계에서 빼야 한다. kind는 5% 공시의 신규·증가 방식이다: buy(매수), placement(증자·전환사채), control(경영권 인수), non_trade, unknown.
| Name | Type | Req | Description |
|---|---|---|---|
| days | number | – | Look-back window in calendar days, counted by filing date (as_of). Default 7, up to 730. 공시일 기준 조회 기간(일). 기본 7, 최대 730 |
| entity_id | number | – | entity_id from search_holder. search_holder의 entity_id |
| holder | string | – | Part of the filer's name. May mix namesakes; prefer entity_id. 보고자명 일부. 동명이인이 섞일 수 있어 entity_id가 낫다 |
| limit | number | – | Maximum rows, default 50. Raise it if the feed looks cut off at exactly limit rows. 최대 행 수, 기본 50. 딱 limit건이면 잘린 것이니 올린다 |
| ticker | string | – | Ticker code or exact Korean company name; limits to that stock. Combines with holder/entity_id. 종목코드 또는 정확한 종목명. 주면 그 종목만, holder·entity_id와 함께 쓸 수 있다 |
No output schema declared.
No examples provided.
search_holder ~375
Find a holder (institution, asset manager, or individual) by name. Korean input also matches foreign filers (블랙록 → BlackRockFundAdvisors). Different people or companies with the same name are separate rows: kind is person/corp/inst; role is, for an individual, the company and title from their latest insider report (e.g. Samsung Electronics chairman); key_hint is the leading digits of a company's business registration number. top is the stock where the holder's stake is highest, corps is the number of stocks reported. Pass entity_id from the result as entity_id to get_portfolio, get_recent_changes and get_holder_history. A row with entity_id null bundles unverified reports under that name and can only be queried by holder name. 보유자(기관·운용사·개인) 이름으로 보유자를 찾는다. 한글로 쳐도 영문 보고자가 나온다(블랙록 → BlackRockFundAdvisors). 같은 이름의 다른 사람·회사는 행이 나뉜다: kind는 person(개인)/corp(법인)/inst(기관), role은 개인의 최근 임원·주요주주 보고 기준 회사와 직함(예: 삼성전자 회장), key_hint는 회사의 사업자등록번호 앞자리. top은 지분율이 가장 높은 종목, corps는 보고한 종목 수. 결과의 entity_id를 get_portfolio·get_recent_changes·get_holder_history의 entity_id로 쓴다. entity_id가 null인 행은 그 이름의 미확인 보고 묶음이며 holder 이름으로만 조회된다.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Part of a holder name, Korean or English. 보유자 이름 일부(한글·영문) |
No output schema declared.
No examples provided.
search_symbol ~307
Find a currently listed Korean stock (KOSPI/KOSDAQ) by part of its Korean or English name, or by ticker code. Returns a list of up to 20 matches as {ticker, name}: an exact name match first, then by market cap. An empty list means no listed stock matched (delisted stocks are excluded). Pass ticker to get_holders, get_holder_history, get_avg_cost or get_recent_changes. To find a person, fund or company as a holder, use search_holder instead. 지금 상장된 한국 종목(코스피·코스닥)을 한글·영문 종목명 일부나 종목코드로 찾는다. 최대 20건의 {ticker, name} 목록을 주며 이름이 정확히 같은 종목이 먼저, 그다음 시가총액 순이다. 빈 목록이면 맞는 상장 종목이 없다(상장폐지 종목은 빠진다). ticker를 get_holders·get_holder_history·get_avg_cost·get_recent_changes에 넘긴다. 보유자(사람·펀드·회사)를 찾으려면 search_holder를 쓴다.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Part of a company name (Korean or English) or a 6-digit ticker code, e.g. 삼성전자, Samsung, 005930. 종목명 일부(한글·영문) 또는 6자리 종목코드 |
No output schema declared.
No examples provided.
How do I install the HOLD! Korea Stock Ownership & Insider Trades MCP server?
HOLD! Korea Stock Ownership & Insider Trades is a hosted endpoint at https://whohold.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · whohold.com
claude mcp add --transport http oon4am-eng-hold 'https://whohold.com/mcp'
What is the HOLD! Korea Stock Ownership & Insider Trades MCP server?
HOLD! Korea Stock Ownership & Insider Trades is an MCP server listed in the public MCP registry as io.github.oon4am-eng/hold. Who owns Korean listed stocks, from DART filings: 5% holders, insiders, stake changes, average cost. This page covers its hosted endpoint (https://whohold.com/mcp).
Is the HOLD! Korea Stock Ownership & Insider Trades MCP server safe to use?
HOLD! Korea Stock Ownership & Insider Trades scores 25 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the HOLD! Korea Stock Ownership & Insider Trades MCP server expose?
HOLD! Korea Stock Ownership & Insider Trades exposes 10 tools: search_symbol, search_holder, get_holders, get_holder_history, get_portfolio, and 5 more. Their descriptions and schemas cost roughly 5,281 tokens of context every time the server is loaded.
Does the HOLD! Korea Stock Ownership & Insider Trades MCP server require authentication?
Its publisher declares no required credentials for HOLD! Korea Stock Ownership & Insider Trades. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.
Is the HOLD! Korea Stock Ownership & Insider Trades MCP server still maintained?
HOLD! Korea Stock Ownership & Insider Trades is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the HOLD! Korea Stock Ownership & Insider Trades MCP server?
VerifyMCP ran 5 checks on HOLD! Korea Stock Ownership & Insider Trades, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 1 more. 6 items could not be completed, a gap on our side rather than a finding about HOLD! Korea Stock Ownership & Insider Trades: Authorization, Schema quality, Stability, Tool coverage and 2 more. 5 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.