Responded16 / 22 checks passed
Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
- Passed: Handshake
- Passed: Tools listed
- Passed: Updated recently
Median latency 132 ms · Last checked
Independent monitoring
Health & checks
Responded
The server completed its last measured handshake. This is an observation, not a guarantee.
Last checked| Test area | Passed | Failed | Unmeasured |
|---|---|---|---|
ConnectionCan a client connect and discover tools? | 5 | 0 | 0 |
Reliability & speedDoes it respond consistently and quickly? | 1 | 0 | 3 |
Access & authenticationWhat is required to use this server? | 1 | 0 | 2 |
Tool qualityAre the tool definitions usable by an agent? | 3 | 1 | 0 |
Publisher identityCan the publisher be traced to its source? | 4 | 0 | 2 |
Unmeasured means there is not enough evidence to decide. How these checks work
Inspect individual checks 22 recorded
Core
- Pass
- Pass
- Pass
- Pass
- Pass
Performance
- Not measured
- Not measured
- Not measured
- Pass
Access
- Pass
- Not measured
- Not measured
Tools
- Pass
- Pass
- Pass
- Fail
Publisher
- Pass
- Not measured
- Pass
- Pass
- Pass
- Not measured
Start using Bamsai
Connect to this server
Choose your client, copy the configuration, then enable the server in your client’s MCP settings.
Run this command in your terminal, then restart Claude Code.
Claude Code
claude mcp add --transport http bamsai https://bamsai.kr/api/mcpCapabilities
Tools 5
get_arbitrage
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
Discoveredget_convergence_history
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
Discoveredget_news
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
Discoveredpredict_open
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
Discoveredpreview_pair_order
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
DiscoveredRecent measurements
Probe history
| Checked | Result | Response | Tools |
|---|---|---|---|
| Connected | 1306 ms | 5 | |
| Connected | 1774 ms | 5 |