Skip to main content
Glama
INo-xious

stockbit-mcp

by INo-xious
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

bandar_detector

Read-only

Analyze broker summary for one IDX stock to detect bandar activity: net buy/sell totals, top accumulators/distributors, and concentration per side.

Instructions

A typed accumulation/distribution reading for one IDX stock, computed from the same broker summary broker_summary returns: net buy and net sell totals for the window, the top accumulators and distributors, and how concentrated each side is. It returns no verdict, no score and no price forecast. A broker code is a pipe carrying thousands of unrelated clients, not a person — the bandar-check skill has the rest of what this cannot prove, and reading it before drawing a conclusion is the difference between flow and a story. SIGNS: values are IDR, volumes are LOTS. Sell figures are NEGATIVE — sellValueIdr, sellLots, and netValueIdr on anything in topDistributors — because that is how Stockbit sends them. Do not negate them again. netValueIdr is buyValueIdr minus the MAGNITUDE of sellValueIdr: how lopsided the two sides are, not how much was bought. Near zero is the normal reading of a complete NET table, since both sides describe the same trades from opposite ends. A large magnitude means they do not cover the same trades — usually truncation, sometimes GROSS. limit applies PER SIDE, so equal list lengths prove nothing; check whether buyersListed or sellersListed has REACHED limit, and if so raise it and see whether the totals move. topDistributors is largest seller FIRST, by size of flow. Concentration shares are fractions of one side taken on magnitudes, so both sides are positive; a null share means the question cannot be asked — that side is empty, or none of its figures could be read. unreadable.buyers / .sellers count listed brokers left out of that side's totals, so buyers: 1 against buyersListed: 16 means every buy figure covers 15 brokers. Broker codes come back bare unless you pass resolve_names: true, which adds each house as name on the two lists by joining against the cached brokers directory. Best-effort: if the directory cannot be read every figure is unchanged and names.note says why, and a code the directory does not carry simply has no name. DATES: omit from/to for the latest session, or supply BOTH (YYYY-MM-DD). A half-specified range is rejected because the API would silently answer with the latest session instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoRange end, YYYY-MM-DD (inclusive). Requires `from`.
topNoBrokers to keep per side (default 5, max 50)
fromNoRange start, YYYY-MM-DD. Requires `to`.
limitNoMax brokers per side fetched from the summary (default 50). Raising it widens the totals and the concentration denominators; it is not the same as `top`, which only trims the two lists that are returned.
periodNoPreset window instead of from/to — LATEST (default), YESTERDAY, LAST_7_DAYS, LAST_3_MONTHS, YEAR_TO_DATE. Aggregated server-side in one request, so YEAR_TO_DATE costs the same as today. Ignored when from/to are given.
symbolYesIDX ticker, e.g. BBRI
date_toNoAlias for `to`.
end_dateNoAlias for `to`.
date_fromNoAlias for `from`.
start_dateNoAlias for `from`.
market_boardNoDefault REGULER — the ordinary order book, and what bandarmology means. ALL folds in negotiated blocks and can be several times larger.
investor_typeNoDefault ALL
resolve_namesNoAdd each broker's securities house as `name`, joined from the cached directory.
transaction_typeNoNET (default) nets each broker's buys against its sells; GROSS does not.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.3.0
    • addedInput schema / properties / resolve_names
      Added value: +{
+  "description": "Add each broker's securities house as `name`, joined from the cached directory.",
+  "type": "boolean"
+}
  2. Addedv1.2.2

TDQS

A4.9/5.0
Behavior5/5

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

The description goes well beyond the annotations, disclosing that sell figures are negative, netValueIdr is a lopsidedness measure rather than bought volume, topDistributors is ordered largest seller first, null shares indicate an unreadable side, and limit applies per side. It also documents resolve_names best-effort failure modes and date rejection behavior, with no contradiction against the readOnlyHint or destructiveHint annotations.

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 long, but it is organized with clear sections like SIGNS and DATES, front-loaded with the core purpose, and every paragraph carries substantive operational detail. It sacrifices brevity for completeness, and a few rhetorical embellishments could be trimmed, but the structure keeps it navigable.

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?

With 14 parameters and no output schema, the description covers sign conventions, edge cases, failure modes, naming behavior, date rules, and the meaning of result fields. An agent has enough information to call the tool correctly and interpret its response without needing external documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema coverage is 100%, the description adds real meaning beyond the schema: limit is explicitly contrasted with top, GROSS vs NET behavior is explained, period aggregation cost is noted, and resolve_names semantics are fully described. This gives the agent a much richer understanding of how parameters change both the request and the interpretation of results.

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 opens with a specific, unambiguous statement: it is a typed accumulation/distribution reading for one IDX stock, computed from the same broker summary that broker_summary returns. It names the outputs — net buy/sell totals, top accumulators/distributors, concentration — and explicitly says it returns no verdict, score, or price forecast, which separates it clearly from related tools.

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?

The description explicitly tells the agent when this tool is not enough and directs it to the bandar-check skill before drawing a conclusion. It also gives concrete invocation rules: omit from/to for the latest session, supply both for a range, a half-specified range is rejected, and market_board ALL behaves differently from REGULER.

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