# Bamsai (remote · bamsai.kr)

Korean blue chips priced 24/7 from Hyperliquid perps in KRW: pre-open price and arbitrage

- Trust score: 72/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `bamsai.kr`: 72/100 (this document), [markdown](https://verifymcp.io/servers/eddyparkgg-bamsai/api-mcp.md), [page](https://verifymcp.io/servers/eddyparkgg-bamsai/api-mcp)

## Channel facts

- Endpoint: `https://bamsai.kr/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 902 tokens (~180/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Bamsai MCP server?

Bamsai is a hosted endpoint at https://bamsai.kr/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http eddyparkgg-bamsai 'https://bamsai.kr/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "eddyparkgg-bamsai": {
      "url": "https://bamsai.kr/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "eddyparkgg-bamsai": {
      "type": "http",
      "url": "https://bamsai.kr/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.eddyparkgg-bamsai]
url = "https://bamsai.kr/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "eddyparkgg-bamsai": {
      "type": "remote",
      "url": "https://bamsai.kr/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add eddyparkgg-bamsai --url 'https://bamsai.kr/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  eddyparkgg-bamsai:
    url: "https://bamsai.kr/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "eddyparkgg-bamsai": {
      "Transport": "http",
      "Url": "https://bamsai.kr/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add eddyparkgg-bamsai -t streamable-http -u 'https://bamsai.kr/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "eddyparkgg-bamsai": {
      "type": "http",
      "url": "https://bamsai.kr/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-08 (score 66, +1)

- [security] Tool “get_arbitrage” rewrote its description, which is the text the model reads
- [security] Tool “get_news” rewrote its description, which is the text the model reads
- [security] Tool “predict_open” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 155 → 180
- [functional improvement] Tool coverage: 80% → 100%
- [cosmetic] “get_convergence_history” reworded the description of “limit”
- [cosmetic] “preview_pair_order” reworded the description of “direction”

### 2026-11-07 (score 65, +1)

- [security] Tool “get_arbitrage” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 121 → 155
- [functional improvement] Tool coverage: 63% → 80%
- [functional improvement] Stability: unverified → 0.03
- [cosmetic] “get_arbitrage” added an optional parameter “lagSec”
- [cosmetic] “get_arbitrage” added an optional parameter “notionalKrw”
- [cosmetic] “preview_pair_order” reworded the description of “notionalKrw”

## MCP tools (5)

### `get_arbitrage` (~259 tokens)

Premium between Hyperliquid perp (mid) and KRX price, its usual level (5-day regular-session median) and the net left after costs on the gap beyond that level. net.netPct subtracts fees, tax, FX, funding, order-book slippage for notionalKrw (net.costs.slippage, net.fills: volume-weighted fill prices per leg) and the price move during the gap between the two orders (net.costs.latency = 1-minute volatility × √(lagSec/60)). net.depthLimited / net.maxNotionalKrw: the visible book can fill less than notionalKrw. oracle.active: oracle-anomaly window (thin print moved the oracle); numbers stay on the real book, oracle.warning flags liquidation risk. All assets if asset is omitted

Input parameters:

- `asset` (string): SMSN=Samsung Electronics, SKHX=SK hynix, HYUNDAI=Hyundai Motor, SKHY=SK hynix ADR (vs 0.1 common share)
- `lagSec` (number): Seconds between the two orders (default 3)
- `notionalKrw` (number): Trade size per leg in KRW (default 10000000)

### `predict_open` (~206 tokens)

Where the next domestic re-open (08:00–08:10 average on KRX/NXT, vs the 20:00 close) stands, for SMSN/SKHX/HYUNDAI. While the domestic market trades, status=in-session and preOpen is Hyperliquid at today's 08:00 open. Otherwise: the Hyperliquid price in KRW now and at the US close, how often past re-opens followed Hyperliquid at this stage of the night (night.follow.ratePct), the 80% band, and the overall follow rate (backtest.followRatePct). probUp and the expected price are model output, not a promise. oracle.active: oracle-anomaly window; the Hyperliquid price then is oracle.robustKrw (30-minute median), not the spiking live mid

Input parameters:

- `asset` (string, required): SMSN=Samsung Electronics, SKHX=SK hynix, HYUNDAI=Hyundai Motor

### `get_convergence_history` (~118 tokens)

Past re-open record per day since 2026-04-13: Hyperliquid move while closed (20:00→08:00), actual re-open move, follow (yes/no/flat), and where the prices met. Newest first, 20 days unless limit is given

Input parameters:

- `asset` (string, required): SMSN=Samsung Electronics, SKHX=SK hynix, HYUNDAI=Hyundai Motor
- `limit` (number): How many most recent re-opens to return (default 20)

### `get_news` (~106 tokens)

One sourced news item per day for an asset (the day's main issue, with title, summary and source link), to explain big overnight or opening moves

Input parameters:

- `asset` (string, required): SMSN=Samsung Electronics, SKHX=SK hynix, HYUNDAI=Hyundai Motor, SKHY=SK hynix ADR (0.1 share), KR200=KOSPI 200, EWY=MSCI Korea ETF, KORU=3x Korea ETF

### `preview_pair_order` (~213 tokens)

Preview (dry-run) of an arbitrage pair order: stock quantity and the Hyperliquid order it would send. Nothing is ever sent from this server. Hyperliquid side is priced on testnet (the default network), so its price can differ from mainnet

Input parameters:

- `asset` (string, required): SMSN=Samsung Electronics, SKHX=SK hynix, HYUNDAI=Hyundai Motor, SKHY=SK hynix ADR (0.1 share), KR200=KOSPI 200, EWY=MSCI Korea ETF, KORU=3x Korea ETF
- `direction` (string, required): perp_short_stock_long = sell the Hyperliquid perp and buy the stock (the only direction retail can do without short-selling stock). Use net.direction from get_arbitrage
- `notionalKrw` (number, required): Trade size in KRW. get_arbitrage with the same notionalKrw shows the expected fill prices, slippage and net for this size

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/eddyparkgg-bamsai/api-mcp#diagnostics

## Score history

- 2026-11-21: 72
- 2026-11-20: 71
- 2026-11-19: 71
- 2026-11-18: 71
- 2026-11-17: 70
- 2026-11-16: 70
- 2026-11-15: 69
- 2026-11-14: 69
- 2026-11-13: 68
- 2026-11-12: 68
- 2026-11-11: 67
- 2026-11-10: 67
- 2026-11-09: 66
- 2026-11-08: 66
- 2026-11-07: 65
- 2026-11-06: 64

## Common questions

### What is the Bamsai MCP server?

Bamsai is an MCP server listed in the public MCP registry as io.github.eddyParkGG/bamsai. Korean blue chips priced 24/7 from Hyperliquid perps in KRW: pre-open price and arbitrage. This page covers its hosted endpoint (https://bamsai.kr/api/mcp).

### Is the Bamsai MCP server safe to use?

Bamsai scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Bamsai MCP server expose?

Bamsai exposes 5 tools: get_arbitrage, predict_open, get_convergence_history, get_news, preview_pair_order. Their descriptions and schemas cost roughly 902 tokens of context every time the server is loaded.

### Does the Bamsai MCP server require authentication?

No. We connected to Bamsai without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Bamsai MCP server still maintained?

Bamsai is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Bamsai MCP server?

VerifyMCP ran 12 checks on Bamsai, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Bamsai: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://bamsai.kr/api/mcp
- Repository: https://github.com/eddyParkGG/bamsaikr
- Website: https://bamsai.kr/developers
- Changelog RSS feed: https://verifymcp.io/servers/eddyparkgg-bamsai/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/eddyparkgg-bamsai/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/eddyparkgg-bamsai/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/eddyparkgg-bamsai/api-mcp
