Skip to main content
Glama
stockbit-mcp

stockbit-mcp

Result of a saved or preset screener

screener_result
Read-onlyIdempotent

Run a saved, preset, or guru screener by ID to retrieve matching stocks and their criteria results; paginate until no rows remain.

Instructions

Runs a saved or preset screener by id and returns the matching stocks.

Returns (Stockbit's data field): data{screenerid, screen_name, screen_desc, type ('TEMPLATE_TYPE_CUSTOM'|'TEMPLATE_TYPE_GURU'|preset type), universe (JSON string), rules[] (echo, with item1_name/item2_name), columns[{id, name, removable}], sequence[] (column ids), order (ordercol), sort ('ASC'|'DESC'), curpage, perpage, totalrows, favorite, calcs[{company{id, symbol, name, icon_url, badges{is_new}}, results[{id, item (column name), display (formatted value)}]}]}. Pagination: increment page until calcs is empty. No matches -> HTTP error with error_type (UI shows 'Tidak ada saham yang sesuai kriteria'). Data freshness (UI footnote): technical/market data refreshed every 15 min, fundamental data end-of-day ~18:30 WIB.

Paywall: unknown (server-side; no client gate found).

Endpoint: GET exodus /screener/templates/{screenerId}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "screenerId": "<screenerId>",
      "type": "<type>"
    },
    "name": "screener_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYesNumeric template type: 1 = TEMPLATE_TYPE_GURU, 2 = TEMPLATE_TYPE_CUSTOM, 0 = anything else (presets)
limitNoRows Default 50.
screenerIdYesPreset, guru or saved screener id

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior5/5

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

Beyond the annotations (which already declare readOnly/idempotent/non-destructive), the description adds substantial behavior: the full return field list, the pagination rule ('increment page until calcs is empty'), the no-match error behavior and error_type, the UI message shown, data freshness windows (15 min technical, ~18:30 WIB fundamental), paywall status, and the raw endpoint. This is exactly the context annotations cannot supply.

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 first sentence front-loads the action and result, and the following material is dense but organized (returns, pagination, errors, freshness, paywall, endpoint). The enumerated return-field dump is long, but with no output schema it earns its place; only the raw endpoint line adds little for an agent.

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 no output schema, the description does the heavy lifting by documenting the response shape, error case, and freshness — enough to call and interpret the tool correctly. It falls short on the pagination input mechanics (no page parameter is exposed despite pagination instructions) and on steering the agent away from similar screener tools.

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 100% and the schema already maps the numeric type values and documents limit, so the baseline of 3 applies. The description repeats the type categories in symbolic form but does not explain how limit interacts with the perpage/curpage fields it describes or how to actually request page N, even though it instructs the agent to paginate — a notable gap given no page parameter exists in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: 'Runs a saved or preset screener by id and returns the matching stocks.' It is clear what the tool does, but it never distinguishes itself from siblings like screener_run, screener_saved, or screener_presets, so an agent cannot route between them from this text alone.

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

Usage Guidelines3/5

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

Usage is only implied: you need a screenerId and a type, and the tool returns matches. There is no explicit statement of when to pick this over screener_run or screener_presets, and no prerequisite call is named (for example, fetching an id from the saved/presets tools).

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