# stockbit-mcp

Indonesian exchange (IDX) via your own Stockbit account: quotes, bandarmology, charts. Unofficial.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 1.4.1
- **Author:** io.github.INo-xious
- **License:** MIT
- **npm:** stockbit-mcp
- **Source:** https://github.com/INo-xious/stockbit-mcp
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 53 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-08-29T09:00:03.608Z
- **Version scanned:** 1.2.1
- **CVEs:** none found by OSV at scan time

## Tools

17 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `deep_dive` — Everything about one stock: quote, technical readings, an annotated chart, and who was on
- `morning_scan` — What moved, and whether the move has anything behind it: today's top gainers, then technical
- `bandar_watch` — Bandarmology for one stock over a window: per-broker net accumulation, then the
- `alert_sweep` — Evaluate every stored alert and chart the ones that fired, so a fired alert arrives with the
- `pine_handoff` — Take an analysis to TradingView: read the levels from Stockbit data, then generate Pine that
- `strategy_check` — Has this actually worked? Read the current technical state, run every built-in strategy over
- `screen_and_dive` — Sweep today's movers for a condition, then look properly at the ones that matched: technical
- `portfolio_review` — Look at what the account ACTUALLY holds, then at each holding properly: who has been on
- `sma_cross` — Long while the 20-day average is above the 50-day.
- `ema_cross` — The same trade on exponential averages, which turn sooner and whipsaw more.
- `golden_cross` — The classic 50/200 crossover. Few trades, long holds — expect a small sample.
- `price_above_ma` — Hold whenever price is above its 50-day average.
- `macd_cross` — Long when MACD crosses above its signal line.
- `rsi_reversion` — Buy the recovery out of oversold, sell into overbought.
- `rsi_trend` — Momentum rather than reversion: long above 50, out below.
- `bollinger_breakout` — Long on a close above the upper band, out at the basis.
- `donchian_breakout` — Long when the 20-day high is taken out, out when the 20-day low is.

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"stockbit\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"stockbit-mcp\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface.
- Floor 13, ceiling 31 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/stockbit-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/stockbit-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/stockbit-mcp
- HTML page: https://forgeregistry.com/registry/stockbit-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.