Undertow market liquidity and exit-cost tools

Daily exit context, depth, tiers, and sealed records. No commodity futures or execution authority.

사용해야 할까요

품질 및 안전성

B
설명 품질
99%
스키마 완전성
55%
이름 품질
80%
오염 위험
100%
권한 일치
100%
프로토콜 준수
100%

도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.

컨텍스트 비용

~1,996토큰 (도구 정의)
~704 B일반적인 응답 크기
중간 정도의 주의 영향 (128k 컨텍스트의 1.56%)

이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.

설치

원클릭 설치

`claude_desktop_config.json` 파일에 다음을 추가하세요:

{
  "mcpServers": {
    "undertow": {
      "url": "https://api.seiche.info/undertow/mcp"
    }
  }
}

원격 엔드포인트

https://api.seiche.info/undertow/mcpstreamable-http

할 수 있는 일

도구 목록

도구 (14)

🟢 읽기 전용🟡 쓰기🔴 삭제⚪ 알 수 없음
🟢agent_access_status

Current identity, freshly checked entitlement, daily usage meter and access instructions. Use when a subscriber tool is missing or refused.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢crypto_exit_check(sizes_usd, max_age_seconds)

Compare up to four BTC sell sizes: exact rungs, brackets or out-of-range. Withholds stale, future, uncovered or unconverted venue estimates. Fees excluded; research only, no trade clearance.

입력 스키마

{
  "type": "object",
  "properties": {
    "sizes_usd": {
      "type": "array",
      "minItems": 1,
      "maxItems": 4,
      "uniqueItems": true,
      "items": {
        "type": "number",
        "minimum": 0.01,
        "maximum": 1000000000000
      },
      "default": [
        1000,
        10000,
        100000,
        1000000
      ]
    },
    "max_age_seconds": {
      "type": "integer",
      "minimum": 60,
      "maximum": 86400,
      "default": 7200
    }
  },
  "additionalProperties": false
}
🟢crypto_funding_cost(notional_usd, side, rate_bps_per_settlement, settlements, round_trip_fee_bps)

Caller-input perpetual funding cashflow, fees, net carry and linear break-even move. Positive funding: longs pay shorts. Constant-rate scenario, not live rates or a forecast.

입력 스키마

{
  "type": "object",
  "properties": {
    "notional_usd": {
      "type": "number",
      "minimum": 0.01,
      "maximum": 1000000000000
    },
    "side": {
      "enum": [
        "long",
        "short"
      ]
    },
    "rate_bps_per_settlement": {
      "type": "number",
      "minimum": -10000,
      "maximum": 10000,
      "description": "1 bp = 0.01%; positive rate means longs pay shorts."
    },
    "settlements": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000
    },
    "round_trip_fee_bps": {
      "type": "number",
      "minimum": 0,
      "maximum": 10000,
      "default": 0
    }
  },
  "required": [
    "notional_usd",
    "side",
    "rate_bps_per_settlement",
    "settlements"
  ],
  "additionalProperties": false
}
🟢crypto_portfolio_stress(equity_usd, positions)

Caller-input linear price shocks on up to twenty exposures: P&L, equity and gross asset/venue concentration. Symbols are scenario labels, not live coverage. No liquidation or probability model.

입력 스키마

{
  "type": "object",
  "properties": {
    "equity_usd": {
      "type": "number",
      "minimum": 0.01,
      "maximum": 1000000000000
    },
    "positions": {
      "type": "array",
      "minItems": 1,
      "maxItems": 20,
      "items": {
        "type": "object",
        "additionalProperties": false,
        "required": [
          "asset",
          "side",
          "notional_usd",
          "price_change_pct"
        ],
        "properties": {
          "asset": {
            "type": "string",
            "pattern": "^[A-Z0-9][A-Z0-9._-]{0,15}$"
          },
          "venue": {
            "type": "string",
            "pattern": "^[a-z0-9][a-z0-9._-]{0,31}$"
          },
          "side": {
            "enum": [
              "long",
              "short"
            ]
          },
          "notional_usd": {
            "type": "number",
            "minimum": 0.01,
            "maximum": 1000000000000
          },
          "price_change_pct": {
            "type": "number",
            "minimum": -100,
            "maximum": 1000
          },
          "cost_usd": {
            "type": "number",
            "minimum": 0,
            "maximum": 1000000000000,
            "default": 0
          }
        }
      }
    }
  },
  "required": [
    "equity_usd",
    "positions"
  ],
  "additionalProperties": false
}
🟢depth_episodes

Realized BTC depth-collapse episodes, onset, trough and recovery under pre- registered rules. Zero episodes is distinct from missing observations. Subscriber exit_desk_full adds ETH.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢exit_cost(size_usd)

BTC sell-cost estimates by venue at the nearest published USD rung. Interpolated bid-depth bands, roughly hourly; fees excluded, not executable quotes. Use crypto_exit_check to compare sizes and freshness.

입력 스키마

{
  "type": "object",
  "properties": {
    "size_usd": {
      "type": "number",
      "exclusiveMinimum": 0,
      "description": "position size in USD (published rungs run $1,000 to $1,000,000; nearest rung is used)"
    }
  },
  "additionalProperties": false
}
🟢latest_article

Read the canonical full-text Undertow editorial with its evidence clock and passing quality receipt; no rewritten facts.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢liquidity_tiers

Nine market-segment tiers plus Seiche funding overlay, exact measure counts, replay eligibility and withholding reasons. PARTIAL may mean missing qualifying history or unpassed replay; it never means calm.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢research_network(topic, offset, limit)

Connected source discovery for Seiche funding, LiquiLens institutions and Palimpsest evidence. Metadata, dates and rights only; no shared score or execution authority.

입력 스키마

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "enum": [
        "all",
        "china",
        "regions",
        "information_controls",
        "model_evaluations",
        "funding",
        "institutions",
        "liquidity",
        "global_data"
      ],
      "default": "all"
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 1000,
      "default": 0
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 2
    }
  },
  "additionalProperties": false
}
🟢sealed_record

Forward calls sealed and signed before outcomes, including misses, decided counts and ledger root. Report hits and misses together.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢trade_safety_exit_context(request_hash, mode, instrument, side, venue, ...)

Exact-rung BTC/USD sell evidence for observe/paper Trade Safety. Binds the opaque request, source pack and reviewed rights to PIT; rechecks USD/USDT conversion, required bid bands, six venue clocks and startup SHA. Context only: no nearest rung, live mode, execution or clearance authority.

입력 스키마

{
  "type": "object",
  "properties": {
    "request_hash": {
      "type": "string",
      "pattern": "^[0-9a-f]{64}$",
      "description": "Opaque complete-request hash"
    },
    "mode": {
      "enum": [
        "observe",
        "paper"
      ]
    },
    "instrument": {
      "const": "BTC/USD"
    },
    "side": {
      "const": "sell"
    },
    "venue": {
      "type": "null"
    },
    "requested_size_usd": {
      "type": "number",
      "enum": [
        1000,
        10000,
        100000,
        1000000
      ],
      "description": "Exact published USD rung"
    }
  },
  "required": [
    "request_hash",
    "mode",
    "instrument",
    "side",
    "venue",
    "requested_size_usd"
  ],
  "additionalProperties": false
}
🟢unwind_watch(cik)

Published watched-filer unwind risk: effective positions, days-to-exit brackets and declared blind spots. Public headline only; no live execution model. Full scenario grid requires unwind_stress.

입력 스키마

{
  "type": "object",
  "properties": {
    "cik": {
      "type": "integer",
      "description": "optional: SEC CIK of a watched filer (returns that filer's full FREE row instead of the all-filer headline)"
    }
  },
  "additionalProperties": false
}
🟢venue_concentration

BTC two-sided depth concentration: HHI, effective venue count, top venue and per- venue depth. Subscriber exit_desk_full adds ETH and the venue-failure scenario.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢venue_price_reconciliation

BTC/ETH consensus mark weighted by depth over squared half-spread, deepest-venue blindness gap, concentration and dislocated venues. Experimental until accrual gates pass; no execution authority.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

커뮤니티

이 서버 평가하기

증거

최근 관측

검증됨버전이 기록되지 않음도구 14개
검증됨버전이 기록되지 않음도구 11개
검증됨버전이 기록되지 않음도구 11개