プロトタイプ · プレビュー版:公式レジストリのすべてのサーバーを掲載し、30分ごとに同期しています。レビューとアカウント機能は今後のステップで始まります。
PopNx MCPAIを使う人のためのMCPサーバー · やさしい言葉で解説

Agentic Finance Graph

作者:AgenticFinanceGraphバージョン 1.7.0i★ –iクラウドで動く
レジストリ名com.agenticfinancegraph/agentic-finance-graph

インストール

概要

作者による説明(英語の原文)

Ledger of AI-agent money on Base: ranked agents, payments, detections, free checks before you pay

PopNx MCPの3つの柱

この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。

できること

このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。

  • 接続方法: クラウドで動く
  • トランスポート: Streamable HTTP
  • カテゴリ: 会計・財務・税務

インストール

使っているAIアプリを選んで、設定をコピーしてください。

インストールの前に

必要なもの

どのアプリを使っていますか?

上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。

ウェブ、デスクトップ、モバイルのClaudeで使えます:

  1. Settings → Connectors を開く
  2. Add custom connector を押す
  3. 下のアドレスを貼り付けて Add を押す
  4. サインインを求められたら、作者のサービスにサインインする
SettingsConnectors1+ Add2https://…3
https://agenticfinancegraph.com/mcp

ターミナルでこれを実行します

claude mcp add --transport http agentic-finance-graph https://agenticfinancegraph.com/mcp

Cursorで開く

または、設定を自分でコピーする

プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます

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

ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。

VS Codeで開く

または、設定を自分でコピーする

プロジェクトの .vscode/mcp.json に貼り付けます

{
  "servers": {
    "agentic-finance-graph": {
      "type": "http",
      "url": "https://agenticfinancegraph.com/mcp"
    }
  }
}

ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。

ChatGPTがつなげるのは、インターネット上のサーバーだけです:

  1. ウェブ版のChatGPTを開き → Settings → Connectors (Apps)
  2. Create または Add を押す(プランによっては、先に Advanced で Developer mode をオンにする必要があります)
  3. 下のアドレスを貼り付け、名前を付けて保存する
  4. サインインを求められたら、作者のサービスにサインインする
SettingsConnectors1+ Create2https://…3
https://agenticfinancegraph.com/mcp

メニューの名前は、プランや時期によって少し違うことがあります。

選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。

この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。

できること

ツールの名前と説明は、サーバーが2026年11月7日に返したそのままの内容です。書いたのは作者で、私たちではありません。プレーンテキストとして表示しています。

  • market_state

    Use this for today's headline figures. 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

  • find_agent

    Use this to look up one or many agents by id, name or wallet; agent_record gives one ranked agent's full record. Look up an ERC-8004 agent by token id on Base, slug, wallet address (0x...) or the name it declares. Returns whether it is ranked, its liveness level (L0-L9), bound wa

  • agent_record

    Use this for one ranked agent's full free record; to look up one or many agents by id, name or wallet, use find_agent. 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

  • ranked_agents

    The top ranked agents (L7 and above: a bound wallet was seen paying money out of the agent's control after registration). Sorted by level first (L9, then L8, then L7), then by lifetime counted USD; sort_by changes the second key to distinct counterparties or number of payments. A

  • detections

    Anomalies our detectors logged, newest first: drain-shaped payments (each with the share of the wallet's balance it took), retry storms, mint bursts, fleet-funding fan-outs (layering_fan), owner changes under a binding, delegation to unknown code. A detection is a shape with evid

  • definition

    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.

  • metric_history

    Use this to chart a figure over time. 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.

  • since_last

    Use this to ask whether a figure moved, and by how much. 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 previou

  • counterparty_preview

    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 l

  • agent_statement

    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. Us

  • evidence_pack_quote

    Price and how to buy a dated evidence pack over x402 (USDC on Base, 1 to 30 cents). About one period: edition (the depth file behind a final State of Agent Money edition: every agent and every payee of the period, the edition's figures and the period's book; id = YYYY-MM, YYYY-Qn

  • pay_check

    Start here before your agent pays or hires another agent. One free call before your agent pays or hires another: its latest statement (stale, age, chain_ok, flags), live incidents, its detections in the last 72 hours, the token approvals its wallet has given (unlimited ones, and

  • payer_set

    The wallets observed paying one agent (income into its bound wallets, plus counted payments from other registered agents), up to 250, with payments, USD and first and last paid; and how much of its ERC-8004 feedback is payment-grounded (the reviewer paid the agent before rating i

  • agent_stability

    The behaviour clock for one ranked agent: run_days (complete UTC days since the last break in its own payment behaviour, by a CUSUM on payments, USD, payees and new-payee share against its own history), the last break's date and feature, and its heartbeat over 30 days (scheduled,

  • agent_independence

    For one ranked agent: its independence score (1 if it paid, in 30 days, an address with demand from three or more operator sets; else half the best score of an agent outside its set that paid one of its payees, best path, at most three hops), the path, its L9 counterparty count u

  • ladder_dynamics

    The whole-cohort document: cumulative incidence of the four competing exits (drained, abandoned, dormant, none) at 30, 60, 90 and 180 days with the numbers at risk and the restricted mean time without an exit (ladder.exit_incidence.v1); the Standardised Drain Ratio per minting ad

  • verify_sum_log

    Trust nothing you did not recompute. Verifies the Ed25519 signature on the current sum-log head (the Merkle-sum root over every counted payment and the total it commits to), optionally climbs one agent's proof from its leaf to the root and the whole total, reports how many of the

  • self_check

    One free call for an agent to check itself, or for the person who runs it: its record and level, the Agent Pass (holds or not, what failed, what could not be checked), the Watch's reading of its newest payment (none / notable / major with reasons), the token approvals its wallet

  • agent_pattern

    Use this to ask whether an agent's newest payment is in character; on its own it is not a pre-payment check (pay_check is). The out-of-character score of an agent's newest counted payment against its own earlier payments (behaviour.out_of_character.v2: amount out of its distribut

  • payee_facts

    Use this for the address your agent was given to pay; for the paying agent itself, use pay_check. What the chain and our ledger say about an address an agent is about to pay (payee.facts.v2): its code kind (plain key, contract, EIP-7702 delegated) and whether the delegate matches

  • gate_check

    Use this when your client applies a written payment policy (AP2 vocabulary) and wants block, warn, log or allow with every reason; it is not a safety verdict, and we never block. One call before an agent pays: the payee facts, the agent's own context from our ledger (what it paid

  • agent_pass

    Use this when you need a signed snapshot to store or show (valid three hours); it is not a prediction. What the ledger measured about one registration at its last evaluation under agent.pass.v2, valid three hours: published level L7+, no open harm-kind incident, a counted payment

  • blast_radius

    For an agent (L8 or above) or one of its bound wallets: priced stablecoin and token balances and ETH in USD at one block, the EIP-7702 delegate if any with its code hash and known sweeper family, and the open ERC-20 allowances the wallet granted, confirmed on chain and capped at

  • canary_register

    Needs a Desk session (Authorization: Bearer); without one this returns 401. Register the public part of a decoy you planted: kind address|key|url|apikey|tool|x402 with exactly one target (address, url_sha256, key_sha256, tool_name or resource_path), a label, the triggers to watch

  • canary_status

    Needs a Desk session (Authorization: Bearer); without one this returns 401. Every canary you registered, with the watcher's last reading (nonce, code, balance, checks) and the newest 20 events per canary (trigger, severity, evidence, whether you declared it a test, the reading in

  • list_metrics

    Every metric the ledger measures or archives: key, unit, definition id, whether it is a headline figure, its first stored sample, and the date from which its history compares across our own changes (comparable_since). Use a filter (part of a key, a definition id or a word from it

基本チェックi

誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月9日にチェック

  • ✓ 合格

    作者とリポジトリが一致

    レジストリ名はドメイン agenticfinancegraph.com で確認済みです(レジストリがドメインの所有を確認しています)

  • … 未チェック

    今もメンテナンスされている

    このリポジトリはまだGitHubから読み取っていません

  • … 未チェック

    ライセンスがある

    このリポジトリはまだGitHubから読み取っていません

  • ✓ 合格

    エンドポイントが応答する

    144ミリ秒で応答(HTTP 200)

  • – 対象外

    OAuthでサインイン

    サインイン不要

  • ✓ 合格

    ツールの説明に隠れた指示がない

    26件のツールの説明を読み、AIへの隠れた指示は見つかりませんでした

会計・財務・税務のほかのサーバーとの比較i

  • このカテゴリのほかの2960件のうち0%よりスターが多い
  • このカテゴリのほかの2960件のうち65%より最近レジストリに公開
  • 基本チェックの結果が、このカテゴリのほかの2960件のうち100%と同じかそれ以上

レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。

よくある質問

Agentic Finance Graphは安全ですか?

当てはまる基本チェック3項目のうち3項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。

どんなキーやコードが必要ですか?

レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。

パソコンで動きますか、それともクラウドですか?

作者のクラウドで動きます。インストール不要でインターネット経由でつながりますが、送った内容は作者のサーバーを通ります。

今もメンテナンスされていますか?

GitHubリポジトリの最終更新は–、最新バージョン(1.7.0)がレジストリに届いたのは17 日前です。

どのアプリで使えますか?

Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。URLでつながるので、リモートMCPサーバーに対応したアプリ(開発者モードのChatGPTなど)でも使えます。

代わりに使えるものは?

同じカテゴリには:Finance Toolkit, SolidInvoice, Korea Tax Calculator

代わりの候補

同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。

カードの見方:↓ 週あたりのダウンロードi★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i

Finance Toolkit

500+ transparent financial methods calculated from raw statements, not third-party endpoints.

作者:JerBouma広く使われている↓ 1.6万/週★ 5496一昨日更新

パソコンでもクラウドでも

SolidInvoice

Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.

作者:SolidInvoice成長中★ 98110 日前更新

クラウドで動く✓ solidinvoice.co

Korea Tax Calculator

Korean tax calculation and tax-audit judgment MCP: 96 tools with statutory citations.

作者:UpstageAI成長中↓ 3172/週★ 97昨日更新

パソコンで動く

作者のREADME

READMEを開く

作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。

Agentic Finance Graph — MCP server and CLI

Ask the independent ledger of machine money directly from Claude, Cursor, an agent framework or your terminal: which AI agents on Base actually pay, how much of their money was really spent, any agent's record, detections, metric histories and the price of an evidence pack.

Read-only and free. Nothing here can move funds, and nothing here needs a key.

Website: agenticfinancegraph.com · Setup guide: MCP server, step by step · Definitions: every figure, defined

Listed in: the official MCP Registry as com.agenticfinancegraph/agentic-finance-graph (publisher verified by domain) · Smithery · Glama (health-checked) · the paid evidence packs in the Coinbase x402 Bazaar and on x402scan

The same data on the website (30 seconds)

https://github.com/user-attachments/assets/ee95c1e9-54c2-49fc-b756-5ab58203861d

*The Desk at agenticfinancegraph.com/desk: connect a wallet, watch any agent, see its history, request the data for 1 cent. The MCP tools below read the same ledger.*

Connect as a remote MCP server (recommended)

Endpoint: https://agenticfinancegraph.com/mcp (Streamable HTTP, stateless, no key).

  • Claude Code: claude mcp add --transport http afg https://agenticfinancegraph.com/mcp
  • Cursor, Windsurf, VS Code and other clients: add a remote MCP server with that URL.

Clients that only speak stdio (Claude Desktop and others)

{

"mcpServers": { "afg": { "command": "npx", "args": ["-y", "github:AgenticFinanceGraph/agentic-finance-graph-mcp", "mcp"] } } }

The mcp command forwards each JSON-RPC message to the remote endpoint. It has no dependencies; Node 18 or newer is enough.

Or run the same bridge in a container (the image holds only the bridge; every answer still comes from the remote endpoint):

docker build -t afg-mcp https://github.com/AgenticFinanceGraph/agentic-finance-graph-mcp.git

docker run -i --rm afg-mcp

Tools

ToolWhat it returns
market_stateHeadline figures, each with value, unit, measurement time and definition id
find_agentAn agent by token id, slug, wallet or declared name, or up to 25 ids at once: rank (and when it last changed), age, wallet, float, payment totals, open incidents
agent_recordThe free record of a ranked agent, with its 25 newest payments
ranked_agentsTop ranked agents (L7+), optionally from a minimum level
detectionsNewest detections, filtered by agent, kind, severity, time or live incidents only
definitionA frozen metric definition: method, exclusions, what it does not claim
metric_historyOne metric over 24h, 7d, 30d or 90d, with its own definition, our dated changes inside the range and the date from which it compares
list_metricsEvery metric we measure: key, unit, definition id, first stored sample, comparable_since
since_lastOne figure beside the stored sample it moved from (previous sample, 24h, 7d or 30d); no prior sample is a gap, never a zero
counterparty_previewWho paid a receiving address: counted payments, distinct payers, distinct L7+ payers (counts only)
agent_statementAn agent's latest 3-hour statement, hash-chained and provable against a signed Merkle root: check it before you pay
pay_checkOne free call before paying an agent: statement freshness and chain, live incidents, detections in the last 72 hours, the token approvals its wallet has given (unlimited ones, and any to a plain account), last payment, payments since the statement, and which refuse conditions are met. Facts, never a verdict
payer_setThe wallets observed paying one agent (up to 250), and how much of its ERC-8004 feedback came from wallets that paid it first. The list is ready to pass to the Reputation Registry's getSummary as clientAddresses
agent_stabilityStable for N days: complete UTC days since the last break in an agent's own payment behaviour (a CUSUM against its own history), the last break, and its 30-day heartbeat (scheduled, irregular, bursty, sparse). A break is a change, not a harm; the measured false-break rate is published
agent_independenceWhether an agent's rank rests on demand outside its own operator set: the seed-based best-path score, its L9 support under the published and the operator-set-aware rule, the inflation ratio, and the size of its operator set
ladder_dynamicsHow ranked agents end (cumulative incidence of drained, abandoned, dormant with numbers at risk), the drain ratio per launch platform with intervals, the day-to-day transition matrix, and the landmark re-check of the survival figures
verify_sum_logThe skeptical client: verifies the Ed25519 signature on the Merkle-sum head over every counted payment, climbs one agent's proof to the root and the total, reports what changed since the head you kept, and verifies the statement log's signed head and consistency proof
agent_patternAdvisory since 1 Nov 2026 (shadow from 16 Oct): is the agent's newest counted payment in character for it (behaviour.out_of_character.v2): level none / notable / major with the reasons that fired, how many of its last 30 days of payments scored, and the market's rates. A level is a pattern for a human to read, never a verdict; nothing is blocked from it
payee_factsNine measured facts about an address an agent is about to pay (payee.facts.v2): code kind and any known sweeper delegate, relay shape, swaps into unfreezable assets, who funds it and where it exits, claim-on-proof selectors, issuer freeze, how many registered agents pay it, the dispersion of prices paid into it, and the paying agent's own history of oversize payments; with the paying agent and the amount, whether it is a never-paid destination at a new size or a look-alike of an address in the agent's history. Each fact carries value, evidence, method and time; an unavailable channel is said, never guessed
gate_checkAdvisory since 1 Nov 2026 (log-only from 16 Oct): can this agent pay this address, now, this much? The payee facts, the agent's own context from our ledger (past-only, never from the caller), the out-of-character level of the payment, and a decision under a policy in the AP2 mandate vocabulary (allowed_payees, amount_range, budget, agent_recurrence, execution_date; ours: new_payee, refuse_conditions, signal) — block / warn / log / allow with every reason, recorded. Unknown constraints fail closed. Named policies: log-only (default), balanced, recommended, recommended-v3, strict. We never block anything; your client decides, and decides its own fail mode
agent_passThe Agent Pass (agent.pass.v2): eight checks on an agent at one moment, valid three hours — level L7+, no open harm-kind incident, a counted payment in 30 days, newest payment in character, no issuer freeze, no unlimited approval to a plain key, no harm-kind incident in 90 days, a month in character. Holds or not, what failed, what could not be checked (listed, never written as 0), the issuer's public key. Shadow: unsigned until the shadow is lifted. It never says safe, verified or trusted
blast_radiusWhat a stolen key would move at one block (agent.blast_radius.v1): priced balances and ETH, the EIP-7702 delegate and any known sweeper family, open allowances confirmed on chain and capped at the balance. Agents at L8 or above, read every six hours
canary_register, canary_statusFor signed-in operators (send Authorization: Bearer with the request): register the public part of a decoy you planted (a bait key that never holds a balance, an address, a URL hash, an API-key hash, a tool name, a paid resource) and read your canaries' state and fires (canary.trigger.v1). Private material is refused before validation; nothing about a plant is ever published
evidence_pack_quotePrice and URL of a paid evidence pack (1 to 30 cents in USDC over x402); it does not pay. precheck (5 cents) is the routine check before you pay or hire an agent, and takes payto, the address you were given; venue (3 cents) says what one address is; builders (1 cent) lists the ERC-8021 Builder Codes on an agent's payments; exit (3 cents) lists the windows in which a new payee took most of an agent's outflow, whether it paid anyone after, and where the money went next (candidates under drain.abandoned.v1, never verdicts); trace (5 cents) follows an agent's exits live up to three hops, with each hop's label, kind, issuer freeze, swap out of a freezable token and Tron activity (check.trace.v1)

market_state, ranked_agents and agent_record also return typed results (structuredContent, described by an outputSchema). market_state carries a composition block (what counted spending consists of, ten parts that add up to the cent) and our data-quality checks; every figure that our own coverage changes touched carries comparable_since, and the dated register of those changes is at /api/changepoints. The server speaks MCP 2025-11-25 and the earlier versions. The same read-only checks also answer over A2A (JSON-RPC message/send) at https://agenticfinancegraph.com/api/a2a; the agent card is at /.well-known/agent-card.json.

Just connected? Tell your AI, in your own words: *"I connected Agentic Finance Graph. Look through what it offers and show me what we can do with it."* The server's instructions tell it how to give the tour with today's figures. Three resources are also served: afg://guide, afg://changepoints, afg://definitions.

Prompts

Ready-made workflows. Clients such as Claude show them in the prompt menu once the server is connected.

PromptWhat it does
start_hereA guided tour with today's real figures: what the ledger measures and the questions worth asking it
daily_briefWhat moved in the last 24 hours: rank, spending and new detections, each figure with its time and definition id
check_before_paying (agent, optional payto)The routine check before your agent pays or hires another: its statement, level and flags, and who has paid the address you were given. It refuses on a stale statement, a broken chain or open flags, and never pays without your approval
explain_agent (agent)One agent in plain words: its level and why, what it paid and to whom, its flags, and what the data cannot show
where_agents_payThe endpoints the most ranked agents pay, with counts

CLI

npx -y github:AgenticFinanceGraph/agentic-finance-graph-mcp state

npx -y github:AgenticFinanceGraph/agentic-finance-graph-mcp find 57657 npx -y github:AgenticFinanceGraph/agentic-finance-graph-mcp ranked 10 9 npx -y github:AgenticFinanceGraph/agentic-finance-graph-mcp history actors_l7_plus 30d npx -y github:AgenticFinanceGraph/agentic-finance-graph-mcp since actors_l7_plus 24h npx -y github:AgenticFinanceGraph/agentic-finance-graph-mcp payers 0x4cd00e387622c35bddb9b4c962c136462338bc31 npx -y github:AgenticFinanceGraph/agentic-finance-graph-mcp statement 53008 npx -y

冒頭だけを表示しています。続きはリポジトリで読めます

PopNxに聞く