# Beepboop2025 Undertow MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.beepboop2025%2Fundertow
Registry id: `mcp-registry/io.github.beepboop2025/undertow`
Status: live (checked 2026-10-27T07:16:27.181Z)

## Measurements (30 days)

- Uptime: 99.98%
- Checks: 5017
- Outages (90 days): 6

## Install

```json
{
  "mcpServers": {
    "beepboop2025-undertow-mcp-server": {
      "type": "http",
      "url": "https://api.seiche.info/undertow/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http beepboop2025-undertow-mcp-server https://api.seiche.info/undertow/mcp
```

## Tools (16)

- `agent_access_status`: Identity, current entitlement, daily usage and access instructions; explains missing/refused subscriber tools.
- `crypto_exit_check`: Compare four BTC sell sizes by rung/bracket. Withholds stale/future, uncovered or unconverted venues. Fees excluded; no trade clearance.
- `crypto_funding_cost`: Caller-input perpetual funding, fees, net carry and linear break-even. Positive funding: longs pay shorts. Constant-rate scenario, not forecast.
- `crypto_portfolio_stress`: Caller-input linear shocks for 20 exposures: P&L, equity, asset/venue concentration. Symbols are scenario labels. No liquidation/probability model.
- `depth_episodes`: Realized BTC depth-collapse onset, trough, recovery under preregistered rules. Zero is distinct from missing. Subscriber exit_desk_full adds ETH.
- `exit_cost`: BTC nearest-rung sell estimates, interpolated bid-depth bands; fees excluded, not executable. crypto_exit_check compares sizes/freshness.
- `gold_cash_realisation`: Calculate gold sale proceeds and cash gates from caller inputs. Decimal strings: kg, fineness (0,1], USD/troy-oz bid, USD fees, currency/USD FX (USD=1). Use awa
- `latest_article`: Read the latest published editorial: title, full text, URL, clock and quality receipt. No arguments. Missing text or failed receipt returns an error; no generat
- `liquidity_tiers`: Nine segment tiers, Seiche funding, measure counts and replay/withholding reasons. PARTIAL means missing history or unpassed replay, never calm.
- `market_corpus_context`: Inspect corpus coverage, rights and clocks. Summary takes no pagination; other views return records/total/next_offset. Retrieval age is not observation freshnes
- `research_network`: Find cross-product source metadata, clocks, rights and next steps. Follow next_offset; unavailable flags retrieval, contract or size failure. Use market_corpus_
- `sealed_record`: Forward calls sealed/signed before outcomes: hits, misses, decided counts, ledger root. Report hits and misses together.
- `trade_safety_exit_context`: Exact-rung BTC/USD observe/paper context: request hash, PIT source/rights, conversion, bid bands, six venue clocks, startup SHA. No live mode or clearance.
- `unwind_watch`: Watched-filer headlines: effective positions, days-to-exit brackets, blind spots. No live execution model. unwind_stress has full scenario grids.
- `venue_concentration`: BTC two-sided depth: HHI, effective/top venue and venue depth. Subscriber exit_desk_full adds ETH and venue failure.
- `venue_price_reconciliation`: BTC/ETH consensus: depth/squared-half-spread weights, deepest-venue blindness, concentration, dislocations. Experimental; no execution authority.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.