xsignal

x402 pay-per-call data tools for Base agents. Flagship get_intent ABSTAINS instead of guessing.

Sollte ich dies verwenden

Qualität und Sicherheit

A
Qualität der Beschreibung
100%
Vollständigkeit des Schemas
98%
Qualität der Benennung
100%
Risiko der Vergiftung
80%
Übereinstimmung der Berechtigungen
100%
Einhaltung des Protokolls
100%

Befunde (2)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains suspicious base64-like encoded stringin get_intent

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

Kontextkosten

~1,125Tokens (Tool-Definitionen)
~734 BTypische Antwortgröße
Mittlere Auswirkung auf die Aufmerksamkeit (0.88% 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": {
    "xsignal": {
      "url": "https://xsignal-production.up.railway.app/mcp"
    }
  }
}

Remote-Endpunkte

https://xsignal-production.up.railway.app/mcpstreamable-http

Was es kann

Tool-Inventar

Tools (6)

🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟡get_intent(addr, min_confidence, question)

FLAGSHIP. An outcome-priced momentum verdict that ABSTAINS below your confidence bar - the only x402 signal that refuses to answer (honestly) when it is not sure. Post {addr, min_confidence 0-1} then pay $0.01, and get a mechanical momentum verdict "gaining" or "fading" IF the signal agreement clears your bar, else a calibrated "abstain". Paid answers carry a keyless tamper-evidence receipt. confidence is a transparent heuristic, NOT a prediction; not financial advice. x402-paid at GET/POST /intent (3 free calls per wallet via ?wallet=0x…). Example: GET /intent?addr=0x4ed4E862860beD51a9570b96d89aF5E1B0Efefed&min_confidence=0.7

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "addr": {
      "type": "string",
      "description": "0x Base token address to read momentum for"
    },
    "min_confidence": {
      "type": "number",
      "description": "0-1; abstain (no verdict, you still pay the flat fee) if mechanical confidence is below this. Default 0.6"
    },
    "question": {
      "type": "string",
      "description": "optional free-text label / social query; defaults to the token symbol"
    }
  },
  "required": [
    "addr"
  ]
}
🟢get_token_brief(addr, query)

A fused MEAL: one call combines Base token market intel + real-time social signal into a single "what is happening with $TOKEN right now" brief - market flags + top CITED social posts + a plain-language, non-advisory summary. Saves an agent the fetch-and-fuse work. x402-paid at GET/POST /brief ($0.05; 3 free per wallet via ?wallet=0x…). Example: GET /brief?addr=0x4ed4…&q=degen

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "addr": {
      "type": "string",
      "description": "0x Base token address"
    },
    "query": {
      "type": "string",
      "description": "optional topic/symbol for the social half; defaults to the token symbol"
    }
  },
  "required": [
    "addr"
  ]
}
🟢get_signal(query, candidates, terms, source, limit)

Real-time X/social signal for a topic: scored (virality + freshness) and CITED (source urls), deduped and ranked. Input: query (topic) OR candidates[] (bring your own posts to score). x402-paid at GET/POST /signal ($0.01; 3 free per wallet via ?wallet=0x…). Example: GET /signal?q=base+memecoin

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "the topic/keywords to get a signal for"
    },
    "candidates": {
      "type": "array",
      "description": "optional: your own posts to score instead of a live fetch"
    },
    "terms": {
      "type": "array",
      "description": "optional explicit match terms"
    },
    "source": {
      "type": "string",
      "description": "xsearch | grok (live source, if a key is set)"
    },
    "limit": {
      "type": "integer",
      "description": "max items to return (<=25)"
    }
  }
}
🟢get_token_intel(addr)

Base token MARKET data (liquidity, 24h volume, price + change, pool age, buy/sell flow, mechanical flags) from public DEX pools. Market data, NOT a trust/safety rating. Best used as an input to get_token_brief. x402-paid at GET/POST /token ($0.01; 3 free per wallet via ?wallet=0x…).

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "addr": {
      "type": "string",
      "description": "0x Base token address"
    }
  },
  "required": [
    "addr"
  ]
}
🟢get_preflight(addr)

The Base PREFLIGHT: one call fuses MainStreet on-chain SAFETY (SAFE/WATCH/AVOID + rug flags) with xsignal MOMENTUM (the abstaining read) into a single recommendation (GO / CAUTION / AVOID / AVOID_ENTRY / NEUTRAL / UNVERIFIED) answering "is this token safe to touch AND moving?". Safety GATES momentum - never green-lights a token that can rug. x402-paid at GET/POST /preflight ($0.05; 3 free per wallet via ?wallet=0x…). Input: addr (0x Base token). Not financial advice.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "addr": {
      "type": "string",
      "description": "0x Base token address"
    }
  },
  "required": [
    "addr"
  ]
}
🟢get_screen(addrs)

BATCH watchlist screen: run the preflight (safety ⊕ momentum) over up to 10 Base tokens in one call → which are GO (safe + moving), plus a per-token verdict + a summary count. For an agent screening a watchlist. x402-paid at GET/POST /screen ($0.10; 3 free per wallet via ?wallet=0x…). Input: addrs (array or comma-separated 0x addresses). Not financial advice.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "addrs": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "up to 10 0x Base token addresses"
    }
  },
  "required": [
    "addrs"
  ]
}

Community

Diesen Server bewerten

Nachweis

Aktuelle Beobachtungen

verifiziertVersion nicht aufgezeichnet6 Tools
verifiziertVersion nicht aufgezeichnet6 Tools