What is InFlow and what does it do?
InFlow is a command-line and MCP‑integrated tool for making agentic payments via the Machine Payments Protocol (MPP) and x402. It is built for both automated agents and human users.
@inflowpayai
基本信息
A wallet for your agents to onboard and pay. Agentic MPP / x402 payments from your machine - CLI + MCP server.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"inflow": {
"command": "npx",
"args": [
"-y",
"@inflowpayai/inflow",
"--mcp"
]
}
}
}Authenticate with InFlow
Log out from InFlow
Check authentication status
List the authenticated user's balances
List the authenticated user's configured deposit addresses
Detect a URL's payment protocol(s) and show MPP and x402 challenges together. Read-only probe - no auth, no payment. Read `detected` to choose a pay rail (MPP wins when both are present).
Best-effort cancel of an MPP approval.
Decode a raw WWW-Authenticate: Payment header, or a base64url credential / receipt.
Show the seller's MPP challenge(s) for a URL. Read-only probe - no auth, no payment.
Pay an MPP-protected resource and return the seller response.
Poll the buyer-side state of an in-flight MPP transaction.
List the methods the buyer can pay with - by intent, settlement rail, and currency.
Retrieve the current authenticated user
Best-effort cancel of an x402 approval.
Decode a raw PAYMENT-REQUIRED header value.
Show the seller's PAYMENT-REQUIRED accepts for a URL. Read-only probe - no auth, no payment.
Pay an x402-protected resource and return the seller response.
Poll the signing state of an in-flight x402 transaction.
List the buyer-side capability cache (scheme x network).
InFlow is an agent-native and human-accessible command-line entry point for performing payments via the Machine Payments Protocol (MPP) and x402. It targets both automated agents (e.g., MCP-integrated assistants) and humans using the raw CLI.
Install globally with npm install -g @inflowpayai/inflow or run directly with npx @inflowpayai/inflow. For agents, add the agentic-payments skill via npx skills add inflowpayai/inflow-cli or install the bundled plugin in hosts like Claude Code, Cursor, or Codex. The default MCP entry runs npx -y @inflowpayai/inflow --mcp.
auth, x402, mpp, user, balances, depositAddresses.--format agent rendering.@inflowpayai/inflow.@inflowpayai/inflow-core client in custom scripts.InFlow is a command-line and MCP‑integrated tool for making agentic payments via the Machine Payments Protocol (MPP) and x402. It is built for both automated agents and human users.
Install the binary globally with `npm install -g @inflowpayai/inflow` or run with `npx @inflowpayai/inflow`. For agents, add the skill or plugin as described in the README.
Node.js >= 22 is required. The project is a pnpm + Turborepo monorepo.
Add the `agentic-payments` skill via `npx skills add inflowpayai/inflow-cli`, or install the plugin in Claude Code, Cursor, or Codex (the repo’s plugin files are auto-discovered). The MCP server is bundled and runs `inflow --mcp`.
InFlow is released under the MIT License.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

AI SEO tools for MCP clients — audit whether AI crawlers can read a website, validate JSON-LD and robots.txt, and generate llms.txt, AI-crawler-aware robots.txt, and JSON-LD schema without leaving the conversation.

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
评论