Skip to main content
Glama
zenith-sb-mcp

zenith-sb-mcp

insider_transactions

Read-only

Track disclosed IDX insider and major-holder trades to see if directors, commissioners, controlling shareholders, or 5%+ owners are adding or trimming shares, with before/after holdings and broker.

Instructions

Disclosed transactions by an IDX company's insiders and major holders: directors, commissioners, controlling shareholders and 5%+ owners, with the shares held before and after, the percentage of the company that represents, and the executing broker. This is the second bandarmology signal after broker_summary. broker_summary says which brokers accumulated; this says whether the people who actually run the company did. Rows carry a badges array where SHAREHOLDER_BADGE_DIREKTUR, _KOMISARIS and _PENGENDALI mark a director, a commissioner and a controlling shareholder — that is the difference between an insider trade and a fund rebalancing. LAG: these are IDX/KSEI disclosures, not trades off the tape. A transaction appears days after it happened and the date on a row is the transaction or record date, not the day it was published. Do NOT use this to time an entry; use it to judge who owns the company and whether the people running it have been adding or trimming. Omit symbol for the market-wide feed. Omit everything for the most recent disclosures across IDX. An empty rows is a normal answer: most companies have no insider filing in a given window. DATES: date_start and date_end are both required together (YYYY-MM-DD). A half-specified window is refused here because this API answers one with its default window and HTTP 200, so you would believe you had filtered when you had not. For an open end pass a far date. action_type and source_type filter server-side. Known actions: BUY, SELL, CROSS, TRANSFER, CORPACTION, RIGHT_ISSUE, WARRANT_EXERCISE, MESOP_OPTION, BOND_CONVERSION, STOCK_BONUS, PRIVATE_PLACEMENT, CAPITAL_REDUCTION, PUPS, REVERSE_SPLIT, STOCK_DIVIDEND, TENDER_OFFER — the list is PARTIAL and an unrecognised name is sent rather than refused. When you pass action_type, check actionFilterHonored in the result: false means the server ignored the filter and the rows are unfiltered. insiderId on a row is the handle for insider_ownership and shareholding(mode=investors). Share counts are shares, not lots. limit is capped at 20 and a larger value is rejected before any request is made. That ceiling is this client's, not a documented upstream one: limit=50 came back HTTP 400 INVALID_PARAMETER on one call naming no parameter, and limit=20 — what Stockbit's own client sends — answered, with nothing in between tried. Use page for more rows.

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": "insider_transactions"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo1-based page (default 1). `hasMore` says if another exists.
limitNoRows per page, 1..20; more is refused here. Omit for the server's default.
symbolNoIDX ticker, e.g. BBRI. Omit for market-wide.
insiderNoRestrict to one holder, using the `insiderId` from a previous row.
date_endNoWindow end, YYYY-MM-DD. Requires date_start.
date_startNoWindow start, YYYY-MM-DD. Requires date_end.
action_typeNoFilter by action, e.g. BUY or ACTION_TYPE_BUY. The known list is partial; unknown names are sent.
source_typeNoIDX (exchange filings) or KSEI (custodian records). Omit for both.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/non-destructive, but the description adds materially more: a LAG disclosure (disclosures appear days after the trade and the row date is the transaction/record date, not publication), a warning that action_type may be silently ignored with actionFilterHonored=true being checkable in the result, and a note that share counts are shares not lots. The badges explanation (SHAREHOLDER_BADGE_DIREKTUR/_KOMISARIS/_PENGENDALI) also tells the agent how to separate insider trades from fund rebalancing.

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 purpose, then lag, then date rules, then filter caveats — a sensible ordering. The one wasteful passage is the limit provenance anecdote ('limit=50 came back HTTP 400 INVALID_PARAMETER on one call naming no parameter, and limit=20 — what Stockbit's own client sends — answered, with nothing in between tried'), which is verbose internal reasoning rather than information the agent needs to pick or call the tool.

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-parameter, no-output-schema tool this covers everything an agent needs: scope defaults, the mandatory date pairing, silent filter failures, pagination via page/hasMore, the 20-row ceiling, the share-vs-lot unit trap, and the empty-result case. The insiderId cross-reference to insider_ownership and shareholding(mode=investors) additionally tells the agent how to chain this tool with others.

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 100%, so 3 is the floor; the description earns above that by explaining *why* date_start and date_end must travel together — a half-specified window silently returns a default window with HTTP 200, so a naive caller would believe it had filtered. It also explains the action_type filter is server-side but partial with unknown names sent, and that limit is capped at 20 client-side. Some of this (limit 1..20, date pairing) restates what the schema already says, which keeps it off a 5.

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?

Opens with a specific verb+resource plus the exact holder classes covered (directors, commissioners, controlling shareholders, 5%+ owners) and the fields returned (shares before/after, percentage, executing broker). It explicitly positions itself against the sibling broker_summary ('broker_summary says which brokers accumulated; this says whether the people who actually run the company did'), so the agent can distinguish the two without opening either schema.

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

Usage Guidelines5/5

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

Gives concrete when-to-use guidance ('use it to judge who owns the company and whether the people running it have been adding or trimming') and an explicit exclusion ('Do NOT use this to time an entry'). It also documents default behaviour (omit symbol for market-wide, omit everything for the most recent IDX-wide feed) and pre-empts a false negative by stating an empty rows result is normal.

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