Agentic Finance Graph

Independent ledger of AI-agent money on Base: ranked agents, payments, detections, statements

我該用這個嗎

品質與安全性

A
說明品質
98%
結構描述完整度
86%
命名品質
84%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,815Token(工具定義)
~600 B典型回應大小
中等的注意力影響(128k 上下文的 1.42%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "agentic-finance-graph": {
      "url": "https://agenticfinancegraph.com/mcp"
    }
  }
}

遠端端點

https://agenticfinancegraph.com/mcpstreamable-http

它能做什麼

工具清單

工具(11)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢market_state

The ledger's headline figures for AI-agent money, each with its value, unit, measurement time and definition id. On Base: money agents paid to others after registration (counted), daily spending by the day it was paid (last day, 7-day and 30-day averages), the part that went into positions they still hold, what left their control, the routing hops and pre-registration history excluded, how many agents are ranked (L7+ paid someone, L8 funded, L9 repeat counterparties), agent income, x402 seller inflow, treasuries, concentration, detections and the address-poisoning watch. On other chains: ERC-8004 registrations on seven chains, what registration owners paid on BNB Smart Chain, Ethereum, Arbitrum, OP Mainnet and Polygon, and Solana agent registrations and payments.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢find_agent(query)

Look up one ERC-8004 agent by token id on Base, slug, or wallet address (0x...). Returns whether it is ranked, its liveness level (L0-L9), bound wallet, stablecoin float, payment totals and open incidents.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Token id (e.g. 57657), slug (8004-base-57657) or wallet address (0x...)"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢agent_record(id)

The free record of one ranked agent: rank with evidence, bindings, and its 25 newest payments with counterparties. Unranked ids return not found: an agent never seen paying has no record to sell or show.

輸入結構描述

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Token id, slug or wallet address"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢ranked_agents(limit, min_level)

The top ranked agents (L7 and above: a bound wallet was seen paying a different address after registration), sorted by the ledger's default order. Free tier: up to 25.

輸入結構描述

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10
    },
    "min_level": {
      "type": "integer",
      "minimum": 7,
      "maximum": 9,
      "description": "Only agents at or above this liveness level"
    }
  },
  "additionalProperties": false
}
🟢detections(agent, limit)

Anomalies our detectors logged, newest first: drain-shaped payments, retry storms, mint bursts, owner changes under a binding, delegation to unknown code. A detection is a shape with evidence, never a verdict. Optionally for one agent.

輸入結構描述

{
  "type": "object",
  "properties": {
    "agent": {
      "type": "string",
      "description": "Optional agent id (act_8453_N or token id)"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10
    }
  },
  "additionalProperties": false
}
🟢definition(id)

The frozen definition of a metric: what it counts, the method, what it excludes and what it does not claim. Use the definition ids returned by the other tools.

輸入結構描述

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Definition id, e.g. pay.usd.total.v1"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢metric_history(key, range)

The history of one measured metric from the ledger's archive (daily points, plus 5-minute points for the last 48 hours). Gaps are real gaps, never filled. An unknown key returns similar keys and the full list of archived keys.

輸入結構描述

{
  "type": "object",
  "properties": {
    "key": {
      "type": "string",
      "description": "Metric key, e.g. actors_l7_plus or observed_pay_usd_total"
    },
    "range": {
      "type": "string",
      "enum": [
        "24h",
        "7d",
        "30d",
        "90d"
      ],
      "default": "30d"
    }
  },
  "required": [
    "key"
  ],
  "additionalProperties": false
}
🟢since_last(metric_id, window)

One measured figure with the stored sample it moved from: current, prior, delta, delta_ratio, both timestamps, definition id, unit, and whether the move is material under the published thresholds. window: sweep (the previous stored sample, the default), 24h, 7d or 30d. No prior sample inside the window returns gap: true and no delta; nothing is interpolated. Accepts a metric key or a definition id.

輸入結構描述

{
  "type": "object",
  "properties": {
    "metric_id": {
      "type": "string",
      "description": "Metric key (actors_l7_plus) or definition id (rank.l7plus.v1)"
    },
    "window": {
      "type": "string",
      "enum": [
        "sweep",
        "24h",
        "7d",
        "30d"
      ],
      "default": "sweep"
    }
  },
  "required": [
    "metric_id"
  ],
  "additionalProperties": false
}
🟢counterparty_preview(address)

For one receiving address on Base (or an x402 resource URL listed in the Bazaar): how many counted payments registered agents made into it, how many distinct agents and how many at L7 or above, first and last seen, and the routing hops excluded. Counts only; the payer list with levels, binding confidence and transaction hashes is the counterparty pack. An address that only received routing hops is not a payee. Without an address: the endpoints the most ranked agents pay.

輸入結構描述

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "0x address on Base, or an x402 resource URL; omit for the top endpoints"
    }
  },
  "additionalProperties": false
}
🟢agent_statement(id)

The latest 3-hour statement for one ranked agent: payments out split into spend, routing hops and payments whose receipt is not read yet; what left its control; income; open flags; the hash of the previous statement; and a Merkle proof against the window's Ed25519-signed root. Check before you pay: refuse if stale, if chain_ok is false, or if flags is not empty.

輸入結構描述

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Agent token id, slug or bound wallet"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢evidence_pack_quote(kind, id)

Price and how to buy a dated evidence pack over x402 (USDC on Base). About one agent: liveness, paygraph (where it pays), drain, incidents, peer, bundle, reval (a live re-probe) or statement (its last 24 statements with proofs). About one receiving address: counterparty (which ranked agents paid it). This tool does not pay; an x402-capable client fetches the returned URL, receives HTTP 402 with the exact price, and retries with a signed payment.

輸入結構描述

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "enum": [
        "liveness",
        "paygraph",
        "drain",
        "incidents",
        "peer",
        "bundle",
        "reval",
        "statement",
        "counterparty"
      ]
    },
    "id": {
      "type": "string",
      "description": "Agent token id, slug or wallet; for counterparty, the receiving 0x address"
    }
  },
  "required": [
    "kind",
    "id"
  ],
  "additionalProperties": false
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本11 個工具