VaultVision Hyperliquid Vault Research

Read-only Hyperliquid vault search, risk, drawdown, rankings, TVL, alerts, and comparisons.

Sollte ich dies verwenden

Qualität und Sicherheit

A
Qualität der Beschreibung
100%
Vollständigkeit des Schemas
71%
Qualität der Benennung
93%
Risiko der Vergiftung
100%
Übereinstimmung der Berechtigungen
90%
Einhaltung des Protokolls
100%

Befunde (1)

  • LOWTool 'fetch' suggests web access but openWorldHint=falsein fetch

Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.

Kontextkosten

~1,279Tokens (Tool-Definitionen)
~736 BTypische Antwortgröße
Mittlere Auswirkung auf die Aufmerksamkeit (1.00% von 128k Kontext)

Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.

Installieren

Installation mit einem Klick

Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:

{
  "mcpServers": {
    "vaultvision": {
      "url": "https://vaultvision.tech/mcp"
    }
  }
}

Remote-Endpunkte

https://vaultvision.tech/mcpstreamable-http

Was es kann

Tool-Inventar

Tools (9)

🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟢search(query, limit)

Search current Hyperliquid vault records and canonical VaultVision research pages. Use this standard discovery tool before fetch when the requested entity is ambiguous.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 160
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "default": 10
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}
🟢fetch(id)

Fetch one VaultVision search result by its vault: or page: identifier and return current structured evidence with a canonical URL.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 240
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}
🟢search_vaults(query, min_tvl_usd, max_risk_score, max_drawdown_pct, accepts_deposits, ...)

Filter and sort current Hyperliquid vaults by name, TVL, modeled risk, drawdown, entry quality, and observed deposit status. Returns evidence, not a recommendation.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 160
    },
    "min_tvl_usd": {
      "type": "number",
      "minimum": 0
    },
    "max_risk_score": {
      "type": "number",
      "minimum": 0,
      "maximum": 100
    },
    "max_drawdown_pct": {
      "type": "number",
      "minimum": 0,
      "maximum": 100
    },
    "accepts_deposits": {
      "type": "boolean"
    },
    "entry_label": {
      "type": "string",
      "maxLength": 40
    },
    "sort_by": {
      "type": "string",
      "enum": [
        "relevance",
        "tvl",
        "risk",
        "drawdown",
        "return_30d",
        "entry"
      ],
      "default": "relevance"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10
    }
  },
  "additionalProperties": false
}

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}
🟢get_vault(vault)

Get the latest available VaultVision record for one vault ID, canonical slug, URL, or exact vault name, including risk, drawdown, entry, TVL, and deposit context.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "vault": {
      "type": "string",
      "minLength": 1,
      "maxLength": 240
    }
  },
  "required": [
    "vault"
  ],
  "additionalProperties": false
}

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}
🟢rank_vaults(ranking_type, limit)

Return the current evidence-gated VaultVision ranking snapshot. Ranking is a first-party model and must not be presented as guaranteed future performance.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "ranking_type": {
      "type": "string",
      "enum": [
        "risk-adjusted",
        "verified",
        "estimated"
      ],
      "default": "risk-adjusted"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10
    }
  },
  "additionalProperties": false
}

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}
🟢compare_vaults(vaults)

Compare two to five current vault records side by side using the same timestamped fields. It does not choose a winner or allocate capital.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "vaults": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 240
      },
      "minItems": 2,
      "maxItems": 5
    }
  },
  "required": [
    "vaults"
  ],
  "additionalProperties": false
}

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}
🟢explain_vault_risk(vault)

Explain one vault's current VaultVision risk score, component values, drawdown evidence, and data caveats without converting the model into investment advice.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "vault": {
      "type": "string",
      "minLength": 1,
      "maxLength": 240
    }
  },
  "required": [
    "vault"
  ],
  "additionalProperties": false
}

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}
🟢get_hlp_metrics

Return the current VaultVision record for Hyperliquidity Provider (HLP), including timestamped TVL, performance, drawdown, risk, and deposit context when available.

Eingabe-Schema

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

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}
🟢get_recent_alerts(since_ts, limit)

Return recent rule-based VaultVision vault signals such as risk, entry, TVL, flow, or APR changes. Signals are monitoring context, not execution instructions.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "since_ts": {
      "type": "integer",
      "minimum": 0
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 20
    }
  },
  "additionalProperties": false
}

Ausgabe-Schema

{
  "type": "object",
  "additionalProperties": true
}

Community

Diesen Server bewerten

Nachweis

Aktuelle Beobachtungen

verifiziertVersion nicht aufgezeichnet9 Tools
verifiziertVersion nicht aufgezeichnet9 Tools