inflow
MCP server for agent-native and human-accessible payments using MPP and x402 protocols, enabling payment flows from CLI or agent hosts.
README
inflow
InFlow — agentic MPP (Machine Payments Protocol) / x402 payments from your machine.
The agent-native and human-accessible command-line entry point to InFlow. Agentic buyers perform agent-native payments via MPP and x402; humans hit the same functionality from MCP-integrated assistants or the raw CLI.
New here? Start with the command reference in packages/cli/README.md — it covers auth,
the x402 and mpp command groups, the global flags, and the agent (--format) renderings.
Installing into an agent host? Use the per-surface guide:
docs/development/surfaces-and-testing.md.
Install
npm install -g @inflowpayai/inflow
Or run directly with npx:
npx @inflowpayai/inflow
Use with agents
Install the agentic-payments skill into a skills-aware agent:
npx skills add inflowpayai/inflow-cli
The repo also ships as an installable plugin (skill + MCP server bundled) for plugin-aware hosts:
-
Claude Code — add the marketplace, then install the plugin:
/plugin marketplace add inflowpayai/inflow-cli /plugin install inflow@inflowHere
inflowpayai/inflow-cliis the GitHub repo slug; the marketplace, plugin, and binary are all namedinflow, so the install target isinflow@inflow. -
Cursor / Codex — point the host at this repo; it discovers
.cursor-plugin/marketplace.json,.agents/plugins/marketplace.json, and.codex-plugin/plugin.jsonrespectively.
In every case the plugin bundles the skill and the inflow MCP server (.mcp.json). The default MCP entry runs
npx -y @inflowpayai/inflow --mcp; install the binary globally only for direct CLI use or for hosts configured to run
inflow --mcp from PATH.
Development
This is a pnpm + Turborepo monorepo. Node >= 22 required.
pnpm install
pnpm build
pnpm test
Other useful tasks:
pnpm typecheck
pnpm lint
pnpm typedoc
pnpm changeset
Packages
@inflowpayai/inflow(packages/cli) — the published binary, and the entry point for anyone integrating InFlow. Thin render shell overinflow-core. Seepackages/cli/README.mdfor the full command reference.@inflowpayai/inflow-core(packages/core) — the headless InFlow client behind the binary. One augmented handle per command group (inflow.auth,inflow.user,inflow.balances,inflow.depositAddresses,inflow.x402,inflow.mpp) carrying both protocol primitives and the command-shaped operations, plus the helpers (sanitization, polling, seller-probe) that make both work. Workspace-internal today; seepackages/core/examples/for runnable scripts.
Repository
https://github.com/glowhub-1028/inflow-cli
License
MIT — Copyright (c) 2025-2026 Jarwin, Inc.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.