Agent402.Tools: pay-per-call web tools

Agent402: 500+ tools, metered models and finished reports for AI agents

Live at agent402.tools.

The paid door for AI agents: 500+ tools, metered models and finished reports, paid per call in USDC over x402 and MPP, or by card. The applied layer of Agentic Finance. Open source, self-hostable, MCP-native.

Operated by Havok Holdings LLC · Live · Why pay here · Receipts · Status · Security · Company

Try it in 30 seconds: claude mcp add agent402 -- npx -y [email protected], or paste https://agent402.tools/mcp into any MCP client. The free tier needs no wallet. Verified setup blocks for Cursor, VS Code, Windsurf, Cline, Roo Code, Codex CLI, Gemini CLI, Continue, ElizaOS, Paperclip, HarnessRouter and AgentCore: agent402.tools/guides/agent-hosts (shortlinks agent402.sh/<host>, e.g. agent402.sh/cursor).

Who pays: agents pay per call (from $0.001; models metered under a quoted ceiling and settled at actual usage); people buy finished reports ($2 to $5) and monitors ($5 a month) by card; sites charge crawlers with the tollbooth.

[Live] [Wellknown] [MCP Queen operational grade] [agent402-mcp on Glama] [MCP Registry] [HOL Registry] [CodeQL] [Secret scan] [npm] [npm] [npm] [CI] [License: AGPL-3.0]

What Agent402 is

Agentic Finance is software agents paying and getting paid on their own: discovering a service, paying per request from a wallet over open protocols (x402, MPP), receiving a verifiable receipt, and earning per request in return. Agent402 is its applied layer - explainer: agent402.tools/agentic-finance · glossary.

Selling an x402 API? List it on the index for free at /sell (POST /api/index/register: self-serve, no signup, 0% take). The router sends buyers to a seller once its routes show settled payments from several independent buyers; calls priced at $0.05 or less on Base (up to $0.25 a day per seller and $5.00 a day in all) or $0.01 or less on Solana can be tried before that, marked unproven on the buyer's receipt. Charging crawlers on your own site instead? agent402-tollbooth puts a 402 gate in front of it.

What makes it different: Agent402 is open-source and self-hostable - and a single integration gives a buyer three free primitives over the whole x402 ecosystem:

• Find - /api/find?q={task} resolves a task description to the best-matching tools (route, price, schema, ready example).
• Route - POST /api/route is the neutral Smart Order Router: rank tools across every x402 seller crawled (auto-discovered from the Coinbase CDP Bazaar), health-aware, with include=external to exclude us. The response returns the top N and carries matched for how many scored.
• Leaderboard - GET /api/leaderboard is the public on-chain ranking of x402 sellers by Base USDC settled volume - calls served, totalUsd, unique buyers per seller. It returns the top N, never the whole board (25 by default, 50 the ceiling; totalSellers carries the full count). Pipeline: Bazaar → eth_getLogs → per-call ceiling → aggregate by payTo. Hourly snapshot.

Plus the catalog - 500+ strong: search/answer as the MCP front door, then 500+ tools and curated skill packs (multi-tool workflows callable as MCP prompts) - all runnable yourself, plus agent402-tollbooth - an open pay-per-crawl gate for the other side of x402.

Two doors, two price lists. Agents pay per call in USDC (x402 / MPP) or free via proof-of-work, and a finished report costs $0.60 to $2.00 that way. People pay by card: the same reports at agent402.tools/reports (company dossier, 13F fund report, insider flow, market brief, deep research, FDA recall, domain audit) are $2 to $5, monitors that re-run on change at /monitors are $5 a month, and a prepaid credits key pays per successful call on Agent402's own services (Authorization: Bearer a402_…; /credits says whether packs are on sale). The card price includes payment processing. An agent paying per call pays the lower tool price for the same report.

Two payment wires, one URL. Every paid endpoint accepts x402 (PAYMENT-SIGNATURE, USDC on 13 chains or USDG on Robinhood Chain) and MPP (Machine Payments Protocol, the IETF-track Payment HTTP auth scheme co-authored by Tempo and Stripe): the same 402 carries both, an mppx client pays out of the box, and MPP settles on Base and Celo (USDC), natively on Tempo (USDC.e or PathUSD via Tempo's relay), or by card over MPP (Stripe stripe/charge, offered on routes priced $0.50 and up when the operator configures it). The MPP marketplace lists every MPP seller we can verify live. Details: What is MPP · live MPP settlements.

Framework adapters (drop-in tools for the major agent stacks - auto-payment underneath): [npm] [npm] [npm] [npm] [npm] [npm] [npm] [npm] [npm]

500+ strong - live web search and cited answers as the MCP front door, then ready-to-use web tools and multi-tool skill packs for your AI agent, from one server. Every one priced per call and settled on-chain. Browser rendering, web search, PDFs, images, OCR, live financial/crypto/macro data, SEC EDGAR, deterministic stats, forecasting, and options/bond pricing (Black-Scholes, YTM), compression, and 150+ pure-CPU utilities. Run it yourself for free in 30 seconds (MCP or plain HTTP, no API keys, no signup - the free tier and x402/MPP payments never need a key; only a prepaid credits key is a bearer key), connect it to Claude/ChatGPT/any MCP client, and add your own tools in a few lines. No language model writes a utility tool's answer, and every tool CI can run without a third-party key is re-tested against its own example before every release. The model-backed surfaces are explicit and priced as such: the /v1 gateway (metered under a quoted ceiling, or flat tiers) and the finished report products (/v1/research, /v1/dossier, ... below).

Optionally, the same server can charge per call over the x402 protocol (USDC on Base, Solana, Polygon, Arbitrum, Monad, Celo, Avalanche, Sei, Optimism, Arc, Ink, Stellar & Algorand, plus USDG on Robinhood Chain - 14 chains) - so the instance you self-host for free can also be a hosted, monetized one. Free mode is one setting (FREE_MODE=true); a paid instance needs a payout wallet.

🟢 Hosted demo: agent402.tools · 📖 Wiki · 📦 npm · 🔌 MCP Registry · 🧩 Hosted MCP connector

Run it yourself in 30 seconds

Pick whichever fits. They are all free and need no wallet:

1. Zero install - add the hosted connector to Claude (claude.ai → Settings → Connectors → Add custom connector):

https://agent402.tools/mcp

2. One command - run the MCP server locally (the pure-CPU tools work with no key; it pays the tiny proof-of-work for you):

npx -y [email protected]# in Claude Code:  claude mcp add agent402 -- npx -y [email protected]

3. Clone and host the whole thing (all 500+ tools as an HTTP API + MCP, free mode, no payments):

git clone https://github.com/MikeyPetrillo/Agent402 && cd Agent402npm installFREE_MODE=true npm start          # → http://localhost:3000  (HTTP API + /mcp)

# try a tool over HTTP - no auth in free modecurl -s -X POST localhost:3000/api/hash -H 'content-type: application/json' \  -d '{"text":"hello world","algo":"sha256"}'

4. One-click deploy to Railway (full self-hosted instance - adds optional Postgres + Redis plugins for analytics + response caching):

[Deploy on Railway]

Boots straight from the repo's Dockerfile. Optional plugins are auto-detected via env: add Redis → REDIS_URL enables the upstream response cache (X-Cache: hit|miss), add Postgres → DATABASE_URL enables the public /api/analytics dashboard. No env vars required to boot in free mode.

Pay per call from a wallet

Every paid route answers 402 with both an x402 offer and MPP challenges, so either client pays it. No API key, no signup: the wallet is the account.

MPP (USDC.e or PathUSD on Tempo, listed first in the 402, or USDC on Base or Celo) with mppx:

import { Mppx, tempo, evm } from "mppx/client";const account = (await import("viem/accounts")).privateKeyToAccount(process.env.AGENT_KEY);const res = await Mppx.create({ methods: [tempo.charge({ account }), evm.charge({ account })] }).fetch("https://agent402.tools/api/uuid");

x402 (USDC on Base and other chains) with @x402/fetch:

import { wrapFetchWithPayment } from "@x402/fetch"; import { x402Client } from "@x402/core/client"; import { registerExactEvmScheme } from "@x402/evm/exact/client";const client = new x402Client(); registerExactEvmScheme(client, { signer: (await import("viem/accounts")).privateKeyToAccount(process.env.AGENT_KEY) });const res = await wrapFetchWithPayment(fetch, client)("https://agent402.tools/api/uuid");

More: Paying with MPP · Paying with x402.

What's in the catalog (500+ tools)

Every tool earns its place: priced to market and settled on-chain, and every tool CI can run without a third-party key is tested against its own example on every CI run. CI holds a 400-entry catalog floor and verifies the “500+” claim against the running catalog (scripts/sync-count.js --check). The catalog grows only when a tool is worth calling.

Full schemas live in /openapi.json; a machine-readable catalog is at /api/pricing and /llms.txt. Don't know which tool you need? /api/find?q=<task> resolves a task description to the right tool - route, price, schema, and a ready example - so an agent skips the token-heavy "search around to find a tool" step.

LLM gateway (/v1) - chat, embeddings, rerank, images, speech & finished reports, pay per call

Call a model: the metered route is the default. POST /v1/metered/chat/completions (and the Anthropic Messages and OpenAI Responses twins, /v1/metered/messages and /v1/metered/responses) serves third-party models with no API key, no signup and no account, paid per call in USDC over x402 or MPP (a prepaid credits key also works, see For humans). The 402 quotes this exact request from its own body (the input estimated from its tokens with headroom, plus your max_tokens, at the model's list price plus a fee). On x402, Tempo and credits, settlement never exceeds that quote: an exact payer pays the quote, and an upto payer (where the 402 offers it) or a credits key settles what the answer used; a card payment adds the processor fee.

curl -i -X POST https://agent402.tools/v1/metered/chat/completions -H 'content-type: application/json' \  -d '{"model":"anthropic/claude-haiku-4.5","messages":[{"role":"user","content":"Summarize x402 in one line"}],"max_tokens":200}'# unpaid: HTTP 402 quoting this body; an x402 or MPP client pays the quote and resends

The flat tiers below stay as the predictable-price option: point any OpenAI SDK at base_url = https://agent402.tools/v1 (or /v1/nano, /v1/pro, /v1/premium) for one price per call whatever the length.

Streaming (stream: true), full tools/function-calling passthrough, an opt-in prompt cache on the chat tiers (cache: true → a byte-identical repeat within 10 minutes is free to the payer that paid for it, on a fresh payment of its own: an x402 v2 exact payment signed by the paying wallet's own key, a verified Tempo sender, or the same credits key; the repeat's payment is not charged, except a Tempo transfer sent before the call, which is final when sent; other payers and payment methods, including Solana, Stellar, Algorand, Permit2/upto, x402 v1 and contract wallets, are charged on each call; the same rule covers the embeddings and rerank caches), upstream failover chains that end in a canary-proven model, and a free GET /v1/models listing every model with its tier and caps. A real-money canary buys the core surfaces daily (the chat tiers, the messages and responses wires, embeddings, rerank, image generation and speech) - streaming, routing disclosure, and both cache behaviors included.

Finished report products live on the same /v1 prefix: one paid call returns a complete, cited report (JSON, with a sources appendix) rather than a raw model turn. Every report is grounded in primary data the server fetches itself (EDGAR filings, openFDA, DNS/TLS probes, on-chain reads, a live web search) before synthesis; ipo-report is fully deterministic (no model at all):

Reports are wallet-only (x402 / MPP / prepaid credits, never proof-of-work) and take a few minutes to generate. The same reports are sold to people by card at agent402.tools/reports for $2 to $5 depending on depth. The card price includes payment processing; an agent paying per call over x402 or MPP pays the lower tool price for the same report.

Two companion tools close the loop: POST /api/route/execute ($0.01, with execute-plus $0.05, execute-max $0.55 and execute-pro $3.30 tiers for pricier tools) resolves a task description to the best tool and runs it in one paid call, including, with include:"external", tools sold by other x402 sellers (it routes on proven on-chain settled volume, with one exception - a Base or Solana seller with no history yet is tried only after every proven candidate, under a small per-call ceiling (on Base, also a daily cap per seller), and flagged unproven on the receipt - buys the result from them on the chain you paid on - Base, Solana, Algorand or Tempo - and sells it to you; see the Smart Order Router guide), and POST /api/my-usage ($0.005) returns the paying wallet's own purchase history - no wallet parameter; the x402 payment is the identity, so nobody can read another wallet's profile.

For humans: reports and monitors

The same catalog has a card-paying front door (Stripe Checkout; the operator enables it with STRIPE_SECRET_KEY, otherwise these pages simply do not mount):

A credits key is understood by the SDKs: agent402-mcp reads AGENT402_CREDITS_KEY and agent402-client takes { creditsKey }.

Decide - describe the job, get the plan

POST /api/decide turns a plain-language task into a call-ready plan: which tools, from this catalog and from outside x402 sellers whose 402 was verified in the last week, in what order, with fallbacks, inputs that validate against each tool's schema, and cost and latency estimates. Priced by depth: quick (one best tool), plan (steps and fallbacks) and full (plus a compiled prompt), from $0.005 per decision over x402 or MPP.

curl -X POST https://agent402.tools/api/decide \  -H "Content-Type: application/json" \  -d '{"task":"Check whether wallet 0xd8dA...6045 is on a sanctions list, then list its recent token transfers on Base","depth":"plan"}'

• Neutral ranking. One formula scores every candidate (fit, observed reliability, price, schema quality, freshness) with no term for who sells the tool, and every step says whether the tool is ours (firstParty).
• The fee comes back. A decision paid with a wallet returns its fee as a 24-hour credit toward POST /api/decide/execute, which runs the plan: our tools directly, outside steps bought from the seller and resold at the seller's price plus a disclosed 5% markup. Spend stops at the budget, fallbacks are tried in order, and a run where no step succeeds is not charged on x402. Because it can buy from outside sellers, execute is paid from a wallet (x402, or MPP on a chain).
• On MCP the same pair is decide.plan and decide.execute; decide.feedback (free) records whether a step worked. Page: agent402.tools/decide.

Skill packs - 70+ multi-tool workflows

For jobs that span several tools - "audit a domain", "diagnose deliverability", "work up a time-series", "peel an opaque blob" - Agent402 ships curated skill packs: ordered, typed sequences of tool calls with a Claude-ready prompt template. Callable as MCP prompts (prompts/list → prompts/get { name, arguments }) or plain HTTP at GET /api/skill-packs/{slug}/prompt (every slug is listed in the free JSON index at /api/skill-packs.json). A task-shaped query to catalog.search (the hosted connector's search tool; the older search_tools name still works as an alias) returns the matching pack alongside individual tools.

All 80+ packs at /skills · JSON index at /api/skill-packs.json · on MCP the packs appear under prompts/list so any MCP-aware client picks them up automatically.

x402 Index - Find · Route · Leaderboard

Agent402 is also the open routing + ranking layer for the whole x402 ecosystem: it crawls public x402 sellers (the local catalog + an auto-discovered set from the Coinbase CDP Bazaar, refreshed hourly) and exposes them through three free surfaces - same logic as /api/find: discovery primitives shouldn't cost money.

# "I need an OCR tool - find me the cheapest healthy one anywhere on x402"curl -X POST https://agent402.tools/api/route \  -H 'content-type: application/json' \  -d '{"query":"ocr image to text","top":5}'
# "Who are the most-used x402 sellers right now? (on-chain proof, not self-reports)"curl 'https://agent402.tools/api/leaderboard?top=25&include=external'

Dispatch is labeled, never implied: every /api/route row and /api/index seller carries routerDispatchEligible and routerDispatchReason (crawl_failed, network_unknown, settlement_required, settlement_checked_at_pay_time, eligible, ...); executeVia appears only on a row the router will pay right now (executeViaCallableNow: true), otherwise the tier moves to executeViaWhenEligible. routable is crawl readiness, never a promise to pay. A manifest-priced route is also read live once and then weekly, so the chains its 402 actually offers reach the row even when the seller's manifest lags.

Health-aware: sellers whose last few crawls errored are excluded from the router (a buyer routed to a dead seller wastes money). Healthier sellers also break ties at equal match score and price, so flaky-but-cheap sellers lose to reliable ones. Brand-new sellers (no history yet) get the benefit of the doubt.

Judged fit: the lexical score rewards a listing whose name repeats the task's words, so one seller's twenty narrow routes could out-rank a general tool that does the job. A judgment model now reads a shortlist - at most two rows per seller, plus the best matches from the local catalog - and moves the listing that actually does the task to the top; when several do it equally well, the cheapest wins. It never adds a seller the settlement gate did not admit, it can say "none of these" (route-execute then refuses before anything is paid), and it fails open to the lexical order. The tools themselves still run no model; this is only how the router chooses.

Operators get 3-rail attribution on the dashboard (/api/stats, /__operator, token-gated - it answers 404 without the operator token): USDC vs. proof-of-work vs. heartbeat-probe traffic are counted separately - and the heartbeat rail is gated on a POW_SECRET-signed token (not a spoofable User-Agent), so the operator view reflects real external demand.

For API sellers: /sell is the front door - list an existing x402-speaking API on the index for free with POST /api/index/register (health-routed, 0% take, self-serve, no signup), or install agent402-tollbooth to put a pay-per-crawl gate in front of a site that isn't x402-native yet.

From code, the agent402-client npm package wraps all of this - find() a tool, then call() it, paying automatically (a built-in proof-of-work for free tools, your x402 wallet for paid ones), with caching and idempotent retries:

npm install agent402-client

import { Agent402 } from "agent402-client";import { privateKeyToAccount } from "viem/accounts";const a = new Agent402();                       // free tier (proof-of-work)const out = await a.call("hash", { text: "hello world", algo: "sha256" });
// a prepaid credits key pays wallet-only tools on Agent402's own servicesconst b = new Agent402({ creditsKey: "a402_..." });
// a signer that deposited USDC into Circle Gateway pays the batched accept// where a 402 offers one (no gas per call); off by defaultconst c = new Agent402({ gateway: { signer: privateKeyToAccount(process.env.AGENT_KEY) } });

agent402-client has no dependencies: install viem for privateKeyToAccount, or pass any EIP-712 signer with address and signTypedData.

Live payments view (services/live)

A separate, read-only service that draws x402 payments on Base and MPP payments on Tempo as they settle. It reads public chain RPCs and public discovery listings, holds the last hour in memory, and fans out to browsers over one server-sent event stream; it shares no process, database or key with the API. Hosted at https://live.agent402.tools.

Run it locally (Node 22+, no dependencies):

cd services/livePORT=8090 node server.js      # then open http://localhost:8090node test.js                  # offline tests

Optional settings: LIVE_BASE_RPCS and LIVE_TEMPO_RPCS (comma-separated RPC URLs), LIVE_INCLUDE_UNLISTED=1 (also count Base payments to wallets no discovery listing names), LIVE_INTERNAL_PAYERS (payer wallets to label as test traffic), LIVE_MAX_PAYMENT_USD (default 50).

Plug into your agent framework (zero-dep adapters)

If you're already on one of the stacks below - OpenAI, Anthropic, the Vercel AI SDK, LangChain (JS or Python), LlamaIndex, Strands, Google ADK, or the OpenAI Agents SDK - skip the wiring: there's a drop-in package that turns the Agent402 catalog into native tool objects for your framework, with payment handled underneath (proof-of-work for free tools, x402+USDC when you pass an @x402/fetch):

// e.g. OpenAI - every adapter has the same surface.import OpenAI from "openai";import { agent402Tools } from "agent402-openai-tools";
const openai = new OpenAI();const { tools, execute } = await agent402Tools({ slugs: ["extract", "hash", "render"] });const res = await openai.chat.completions.create({ model: "gpt-4o-mini", tools, messages: [...] });// when the model returns a tool call: await execute(call.function.name, JSON.parse(call.function.arguments));

Already a Claude/MCP user? agent402-mcp is still the better path - paste https://agent402.tools/mcp into your client. The adapters are for direct API integrations where MCP isn't available. Sources: adapters/.

OpenClaw agents: drop in skills/openclaw/agent402/SKILL.md - teaches an OpenClaw agent to find, pay (x402 USDC on Base, twelve other chains accepted, or free proof-of-work), and call any of the 500+ tools and packs.

Add your own tool (~15 lines)

A tool is just an object in a kit array. Drop this into any file in src/tools/ (e.g. append to AGENT_TOOLS in src/tools/agent-kit.js) and it's live - routed, schema-published, MCP-exposed, and covered by the "every tool answers its own example" CI check:

{  route: "POST /api/reverse",  name: "Reverse text",  slug: "reverse",  category: "text",  price: "$0.001",                       // free via proof-of-work once listed in src/free-tier.js  description: "Reverse a string. Example: {\"text\":\"abc\"} → {\"reversed\":\"cba\"}",  discovery: {    inputSchema: { properties: { text: { type: "string" } }, required: ["text"] },    example: { text: "abc" },            // CI calls this and checks it works  },  handler: (input) => {    if (typeof input.text !== "string") { const e = new Error('"text" required'); e.statusCode = 400; throw e; }    return { reversed: [...input.text].reverse().join("") };  },}

That's the whole contract: handler(input) returns a JSON-serializable object (or throws an Error with .statusCode for a 4xx). A new tool is wallet-only; a pure-CPU tool joins the free proof-of-work tier when its slug is added to FREE_TIER_SLUGS in src/free-tier.js. See CONTRIBUTING.md for the full walkthrough.

Optional: charge per call with x402

The same server can require payment per call - useful if you host a public instance. Payments are the default posture: a bare npm start fails closed, exiting unless WALLET_ADDRESS is set - running without payments is the explicit opt-in (FREE_MODE=true npm start). To charge, set WALLET_ADDRESS

• CDP facilitator keys (free at portal.cdp.coinbase.com) and agents pay in USDC on Base (or Solana, Polygon, Arbitrum, Monad, Celo, Avalanche, Sei, Optimism, Arc, Ink, Stellar, Algorand - or USDG on Robinhood Chain via PAYMENT_NETWORKS=…,robinhood + ROBINHOOD_FACILITATOR_URL) via standard x402 clients:

Every 402 is valid under @x402/core's own schemas (at most five tags, CI-checked on all routes) and carries a typed output schema twice: in the bazaar discovery extension and as accepts[0].outputSchema on the first accept, so a client that reads the spec's field sees the response shape before paying.

Optional: GATEWAY_NANOPAYMENTS=on adds a Circle Gateway batched accept on Arc and Base beside the plain one (same price, same payTo; buyers who deposited USDC into Gateway sign per call with no gas, and Gateway settles off chain into your Gateway balance, withdrawn with scripts/gateway-withdraw.js). Off by default; see the wiki's Self-Hosting page. Buyers pay it from agent402-client with the gateway option (wiki: Circle Gateway).

import { wrapFetchWithPayment } from "@x402/fetch";import { x402Client } from "@x402/core/client";import { registerExactEvmScheme } from "@x402/evm/exact/client";import { privateKeyToAccount } from "viem/accounts";
const client = new x402Client();registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });const payFetch = wrapFetchWithPayment(fetch, client);const res = await payFetch("https://agent402.tools/api/extract", {  method: "POST", headers: { "Content-Type": "application/json" },  body: JSON.stringify({ url: "https://agent402.tools/guides/x402-in-5-minutes" }),});

MPP dual-stack. The paywall also speaks MPP (Machine Payments Protocol - the IETF-track Payment HTTP auth scheme from tempoxyz/mpp): the same 402 carries a WWW-Authenticate: Payment challenge, Authorization: Payment credentials settle, and settled responses return a Payment-Receipt. MPP has two methods here: evm settles identically to x402 (EIP-3009 USDC, same facilitator, same price); tempo settles natively via Tempo's own relay (TIP-1034/TIP-20, no x402 facilitator involved) - a genuinely separate settlement path, set TEMPO_API_KEY to enable it. An mppx client works out of the box for either method; set MPP_SECRET_KEY to enable the shim on your own instance. Same URL either way - the buyer's client picks the dialect.

Agents without a wallet still use every pure-CPU tool by solving a single-use sha256 proof-of-work (a fraction of a second on a laptop; the MCP servers do it automatically). Details: wiki: Paying with x402 · Paying with MPP · Paying with Compute.

Why pay here - seven things that are different

Every claim links to the surface that proves it (the live version, a section of the docs: agent402.tools/docs#why).

1. Pay for what the model used, with the ceiling quoted first. The metered gateway (POST /v1/metered/chat/completions) quotes each 402 from the request's own body; a wallet paying upto settles actual usage under that ceiling, provider discounts such as prompt-cache reads pass through, and every settled x402 or MPP response carries a receipt; a JSON answer bought with an EVM wallet can be attested on Base by that wallet (POST /api/attest).
2. A failed x402 call is not charged, and the response proves it. Settlement runs after the handler and an error status cancels it, so a response with no payment receipt, or a receipt marked success:false, moved no money; a retry carrying the same Idempotency-Key and the same payment credential replays the paid answer instead of paying again, and a request re-sent with the same signed EVM payment is answered from its first answer even without a key (X-Replayed-Answer: 1); the one residual case (a settled receipt on an error response) is detected by our own alarm and recorded as a debt in a refund ledger, never written off silently.
3. One key buys everything. The same wallet pays for five LLM tiers on four wires (OpenAI chat, OpenAI Responses, Anthropic Messages, Gemini generateContent), embeddings, rerank, images, video, speech, transcription, grounded answers with citations, 500+ tools and finished reports, and an EVM wallet also keys its own memory.
4. No wallet required. Proof-of-work pays for the pure-CPU tools, cards over MPP pay routes priced at $0.50 or more, and card checkout sells the finished reports, beside USDC or USDG on fourteen chains and native MPP on Tempo.
5. Finished work, ready to use. Dossiers, insider flow, 13F holdings, filing reports, IPO digests, domain audits, token risk, deep research, market briefs, recall watch and a LinkedIn article package, grounded in live sources, most with a downloadable data appendix; monitors check for free on a schedule and re-run the paid report when the facts change, up to 4 full reports in any 30 days.
6. We source from other sellers. POST /api/route/execute resolves a task to the best seller across the ecosystem, buys the result from that seller with our wallet and sells it to you under one receipt. Sellers are routable on proven on-chain settlement, with one bounded exception for a zero-history Base or Solana seller under a small per-call ceiling.
7. Everything is checkable. Uptime observed by two probes outside production (/status), a real-money canary through every on-chain rail daily, transactions published by rail and wire (/revenue), open source and self-hostable. The deterministic tools run no model; the ones that do are named (the /v1 tiers, the report products, the image, speech, transcription, embedding and AI-answer tools, the Decide planner, and the judgment model that can pick among the router's shortlisted candidates). The operator is identified on-chain: Agent402 is agent 94639 in the ERC-8004 Identity Registry on Base, resolving to /.well-known/agent-registration.json, with an A2A agent card at /.well-known/agent-card.json.

Why it's solid

• Everything is tested - CI calls every tool that needs no third-party key with its own documented example and blocks the release on any failure; the key-gated and model-backed tools are covered by input probes and a daily paid canary instead, because CI holds no third-party keys. Two independent probes outside production watch the live instance (one every 5 minutes, on separate infra from the other), and what they observe is public at /status - where a day with no observation reads "no data", never uptime, because an outage is exactly when a probe cannot report.
• Hardened - connect-time SSRF guard on every URL tool (DNS-rebind safe), proof-of-work that's signed/single-use/slug-scoped, per-IP rate limits, and security headers. See wiki: Security Model.
• Deterministic utilities - no model in the serving path of the utility tools: a pure-computation tool returns the same output for the same input, and a live-data tool returns its source's current reading, with full OpenAPI schemas.
• Auditable, on-chain revenue - paid calls on Base settle in USDC to agent402.base.eth (a Base name resolving to the public receiving wallet); every other chain's receiving address is in the live 402 and at /.well-known/x402, so anyone can verify on chain; live counts at /api/stats.
• AGPL-3.0 licensed, self-host-friendly - clone it, strip what you don't need, add what you do.

Agent402 in the x402 ecosystem

x402 is an open payment protocol built on HTTP 402 Payment Required for machine-to-machine, pay-per-call payments in stablecoins (USDC). Most projects in the space are the protocol + SDKs, a starter template, or a payment facilitator. Agent402 is the applied layer - a ready-to-run x402 server that already speaks the protocol and ships 500+ working tools, so you don't have to build the catalog yourself.

• Want the protocol or an SDK? → coinbase/x402.
• Want a server you can run today that actually does things over x402 + MCP? → you're here.
• Self-hostable, free via proof-of-work without a wallet, and non-custodial on the payment tools (your agent signs with its own key and we hold no crypto balance for it; prepaid card credits are a held balance and are named as one).

Listed in the official MCP Registry and discoverable in the Coinbase x402 Bazaar.

Works with AWS Bedrock AgentCore Payments out of the box - AgentCore orchestrates x402, which is the protocol Agent402 already speaks. Point the AgentCore Gateway at https://agent402.tools/mcp for all 500+ tools, or use agent402-strands for a curated subset inside a Strands agent. Five-minute recipe: wiki: AWS Bedrock AgentCore.

Tollbooth - pay-per-crawl for your site (the other side of x402)

Charge AI crawlers that hit your site. Humans browse free; known bots get 402 Payment Required and can pay in USDC over x402 - or solve a free proof-of-work. The open, crypto-native answer to Cloudflare's closed pay-per-crawl: no CDN lock-in, no Stripe, no merchant-of-record, no signup.

• Product page · pricing · live install: agent402.tools/tollbooth
• Run it yourself (MIT, npm): npm i agent402-tollbooth · tollbooth/ · tollbooth/README.md

Runs as Express middleware, a Next.js / Vercel Edge middleware, a Cloudflare Worker, a reverse proxy, or a WordPress plugin (beta). Drop-in templates in tollbooth/deploy/. One Web-Crypto core powers all of them. Since 0.9.x the gate also speaks MPP natively: hand it your @x402/express middleware (createTollbooth({ x402 })) and it mints WWW-Authenticate: Payment evm challenges from the same 402, or give it a Tempo relay key (createTollbooth({ tempo: { apiKey, recipient, currency, splits } })) and it settles MPP tempo/charge credentials on Tempo with optional split payments, with no x402 middleware at all. Since 0.10.0 the edge build speaks MPP too: with secret, payTo and your verifyX402 callback set, every 402 carries a WWW-Authenticate: Payment challenge beside the x402 quote, and an Authorization: Payment credential (HMAC-bound to that challenge, unexpired, minted for that exact resource) is translated to PAYMENT-SIGNATURE and handed to the same verifier.

Repository map

Legal

• The hosted instance at agent402.tools is provided under its Terms of Service (acceptable-use policy included - using the service, including programmatically, constitutes acceptance) and Privacy Policy.
• AI-gateway traffic (/v1 chat, embeddings, images, speech) is additionally subject to the upstream model providers' usage policies. Wallets used for prohibited content are blocked before settlement (WALLET_BLOCKLIST).
• The server code is AGPL-3.0-licensed and provided as-is; every published npm package is MIT with its own LICENSE file in its directory: agent402-mcp (mcp/), agent402-client (client/), agent402-tollbooth (tollbooth/), agent402-openclaw (openclaw/), agent402-agentkit (adapters/agentkit/), elizaos-plugin-agent402 (adapters/eliza/) and the facilitator (facilitator/). GitHub's repository-level license badge reports the server's AGPL; a package's license field and its directory's LICENSE are what apply to that package. Provided as-is, without warranty (see LICENSE and NOTICE). "Agent402" and the logo are trademarks of Havok Holdings LLC - the license covers the code, not the name; forks must rename (see TRADEMARKS.md). If you self-host, you are the operator: your deployment, your terms, your compliance - Havok Holdings LLC operates only the hosted instance and is not responsible for third-party deployments.

Contact

• Email: [email protected]
• X / Twitter: @Agent402Tools
• GitHub: MikeyPetrillo/Agent402

Contributing

PRs that add useful tools, fix bugs, or improve docs are very welcome - see CONTRIBUTING.md. Server AGPL-3.0, every published package MIT (see Legal above). Maintained by Havok Holdings LLC.