P402
БесплатноНе проверенMulti-provider AI router with x402 micropayment settlement on Base L2. 1% flat fee.
Описание
Multi-provider AI router with x402 micropayment settlement on Base L2. 1% flat fee.
README
npm @p402/sdk npm @p402/cli npm @p402/mcp-server npm @p402/mpp-method VS Code Marketplace License: MIT Docs
AI payment router. Route across 300+ models, settle per request in USDC on Base or USDC.e on Tempo.
P402 sits between your AI application and every LLM provider. It handles intelligent multi-provider routing (cost / quality / speed / balanced), on-chain micropayment settlement via the x402 protocol and mppx on Base and Tempo, and spending guardrails for autonomous agents.
Why P402
| Problem | P402 Solution |
|---|---|
| Hardcoded to one AI provider | Route across 300+ models automatically |
| $0.30 payment fees kill micropayments | USDC on Base: fractions of a cent per settlement |
| No spending limits for AI agents | Session budgets + AP2 mandate governance |
| Fragmented provider APIs | One OpenAI-compatible endpoint |
| No visibility into AI costs | Real-time analytics + optimization suggestions |
Quick Start (VS Code / Cursor / Windsurf)
Install the extension — the MCP server is embedded, tools appear in Copilot agent mode immediately, no config files required:
ext install p402-protocol.p402
Then run P402: Configure API Key from the command palette.
→ VS Code Marketplace · Open VSX
Quick Start (Claude Desktop / any MCP client)
{
"mcpServers": {
"p402": {
"command": "npx",
"args": ["-y", "@p402/mcp-server"],
"env": { "P402_API_KEY": "p402_live_..." }
}
}
}
→ MCP docs · MCP Registry
Quick Start (SDK)
npm install @p402/sdk
import P402Client from '@p402/sdk';
const p402 = new P402Client({ apiKey: process.env.P402_API_KEY });
// Drop-in OpenAI replacement — P402 picks the best provider
const response = await p402.chat({
messages: [{ role: 'user', content: 'Explain x402 payments in one sentence.' }],
p402: { mode: 'cost' } // cost | quality | speed | balanced
});
console.log(response.choices[0].message.content);
// p402_metadata: { provider: 'deepseek', cost_usd: 0.00031, latency_ms: 412 }
Quick Start (CLI)
# Authenticate once
npx p402 login
# Chat using the cheapest provider
npx p402 chat "What is x402?" --mode cost
# Check facilitator health
npx p402 health
Routing Modes
| Mode | Optimizes For | Typical Provider |
|---|---|---|
cost |
Lowest price | DeepSeek V3, Haiku 4.5, GPT-4o-mini |
quality |
Best output | Claude Opus 4.6, GPT-5, Gemini 3 Pro |
speed |
Lowest latency | Groq LPU, Flash models |
balanced |
Equal weight (default) | Sonnet 4.6, GPT-4o, Gemini Flash |
Session Budgets
Enforce hard spending caps for autonomous agents:
// Create a $10 session — agent cannot spend a cent more
const session = await p402.createSession({ budget_usd: 10 });
// All chat requests are deducted from the session
const response = await p402.chat({
messages,
p402: { session_id: session.id, mode: 'cost' }
});
// Check remaining budget
const { budget } = await p402.getSession(session.id);
console.log(`$${budget.remaining_usd} remaining`);
x402 Payments
x402 is a machine-native payment protocol using HTTP 402. AI agents pay for resources using gasless EIP-3009 USDC transfers on Base L2.
Client → signs EIP-3009 authorization
→ POST /api/v1/facilitator/verify
→ POST /api/v1/facilitator/settle
Facilitator → executes transferWithAuthorization
→ pays gas (user pays zero gas)
→ returns { success, txHash, receipt }
Network: Base Mainnet (Chain ID: 8453) · Asset: USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
A2A Protocol
P402 implements the Google A2A spec over JSON-RPC 2.0. Agents communicate through structured tasks, discover capabilities via /.well-known/agent.json, and settle payments via the x402 extension.
// Discover P402's capabilities
GET https://p402.io/.well-known/agent.json
// Submit a task
POST https://p402.io/api/a2a
{ "jsonrpc": "2.0", "method": "tasks/send", "params": { ... } }
Packages
| Package | Description | Version |
|---|---|---|
| @p402/sdk | TypeScript SDK — P402Client, types, EIP-712 mandate helpers | npm |
| @p402/cli | CLI tool — login, chat, sessions, mandates, analytics | npm |
| @p402/mcp-server | stdio MCP server — 6 tools over Model Context Protocol | npm |
| @p402/mpp-method | mppx payment methods — Base EIP-3009 and Tempo TIP-20 multi-rail settlement | npm |
| p402 VS Code extension | Embedded MCP server for VS Code, Cursor, and Windsurf — zero config | Marketplace |
Examples
| Example | What It Shows |
|---|---|
| 01-quickstart | Login → chat → view spend in ~20 lines |
| 02-openai-migration | Drop-in OpenAI SDK replacement |
| 03-nextjs-session-budget | Budget-capped AI in a Next.js App Router project |
| 04-a2a-agents | Two agents communicating with x402 payment gate |
Docs
| Guide | |
|---|---|
| Getting Started | Account, API key, first request |
| Authentication | API keys, env vars, security |
| Routing Guide | Modes, scoring, providers, models |
| x402 Payments | EIP-3009, wire format, settlement |
| Sessions | Session lifecycle + budget enforcement |
| A2A Protocol | JSON-RPC, mandates, Bazaar |
| CLI Reference | Full CLI command reference |
| OpenAPI Spec | Machine-readable API schema |
Community
- Dashboard: p402.io/dashboard
- Docs: p402.io/docs
- Issues: GitHub Issues
- Security: See SECURITY.md for responsible disclosure
- Contributing: See CONTRIBUTING.md
License
MIT © P402 Protocol
Установить P402 в Claude Desktop, Claude Code, Cursor
unyly install p402Ставит в Claude Desktop, Claude Code, Cursor и VS Code — сам разбирается с npx, uvx и сборкой из исходников.
Впервые? Поставь CLI: curl -fsSL https://unyly.org/install | sh
Или настроить вручную
Выполни в терминале:
claude mcp add p402 -- npx -y @p402/mcp-serverFAQ
P402 MCP бесплатный?
Да, P402 MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для P402?
Нет, P402 работает без API-ключей и переменных окружения.
P402 — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить P402 в Claude Desktop, Claude Code или Cursor?
Открой P402 на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare P402 with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
