Skip to main content
Glama
stockbit-mcp

stockbit-mcp

Run a stock screener

screener_run
Read-onlyIdempotent

Screens IDX stocks with fundamental, technical, and flow rules and returns matching stocks with metric values as columns. Runs a temporary screen without saving to the account.

Instructions

Screens IDX stocks with rules on fundamental, technical and flow metrics and returns the matching stocks with the metric values as columns. Look up metric ids with screener_metrics and universes with screener_universe first. Runs a temporary screener: nothing is saved to the account. Some metrics (e.g. bandarmology) may need Stockbit Pro.

Endpoint: POST exodus /screener/templates (save "0").

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": {
      "rules": "<rules>"
    },
    "name": "screener_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, from 1.
limitNoHow many rows to return (max 100, default 50).
orderNoSort direction, default desc.
rulesYesThe rules; all must hold.
order_columnNoColumn to sort by: 2 is the first rule's metric, 3 the second, and so on. Default 2.
universe_nameNoUniverse name from screener_universe, default "IHSG".
universe_scopeNoIts scope, default "IHSG".
universe_scope_idNoIts scope id, default "".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds real context beyond them: nothing is persisted to the account, and some metrics such as bandarmology require a Stockbit Pro subscription. The underlying endpoint note (POST templates with save "0") explains why a POST-shaped call is still a non-mutating temporary run.

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 core behavior and return format are front-loaded, followed by prerequisites and the Pro caveat. The trailing endpoint line is implementation detail of marginal value to an agent, but it is short and does explain the non-saving semantics.

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?

For an 8-parameter tool with no output schema, the description covers what comes back (matching rows with metric columns) and where the id/name parameters must be sourced from. Remaining details such as pagination defaults and the meaning of order_column are handled in the schema itself.

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%, including the maxItems:20 rule cap and the 'all' operator behavior, so the schema carries the parameter burden. The description only adds that metric ids come from screener_metrics and universe names from screener_universe, which is useful but minimal. Baseline 3 is appropriate.

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?

States a specific verb and resource (screens IDX stocks) plus the rule inputs (fundamental, technical, flow metrics) and the return shape (matching stocks with metric values as columns). That distinguishes it clearly from the lookup siblings screener_metrics and screener_universe, which it references by name.

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

Usage Guidelines4/5

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

Gives an explicit prerequisite sequence: resolve metric ids via screener_metrics and universes via screener_universe before calling. It also signals the temporary/stateless nature of the run, which implies when this is preferable to a saved screener. It stops short of naming screener_presets or screener_saved as the alternative for persisted screeners.

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