Inflow MCP Server

by inflowpay-app

answering

Inflow is answering right now. Last checked 9 min ago. Last commit 15 Apr 2026.

MCP Server for agents to onboard, pay, and provision services autonomously with InFlow

Uptime history 62 hours of history

62 hours agonow

100.0%

Uptime 24h

92 of 92 checks

—

Tools

hidden behind auth

435 ms

Response time

average over 24h

Stars

last commit 15 Apr 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add inflow --transport http https://app.inflowpay.ai/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "inflow": {
      "url": "https://app.inflowpay.ai/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.inflow]
url = "https://app.inflowpay.ai/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "inflow": {
      "url": "https://app.inflowpay.ai/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "inflow": {
      "url": "https://app.inflowpay.ai/mcp"
    }
  }
}

This endpoint answered with an authorization challenge — the server is running, but you need an API key or OAuth to use it.

Endpoints

URL	Transport	State	Latency	Checked
https://app.inflowpay.ai/mcp	streamable-http	needs key	407 ms	9 min ago

Alternatives to Inflow

same job, measured the same way

Paypal

by paypal-mcp

PayPal MCP server provides access to PayPal services and operations for AI assistants

answering

Ainative Postgres MCP

by ainative-studio

Zero-config Postgres MCP with auto-provisioning — drop-in for server-postgres.

529 installs/wk local only

HPP x402 MCP Bridge

by hpp-io

MCP bridge for autonomous x402 payments in HPP USDC.e — discover and pay for services per call.

705 installs/wk local only

Localstack

by giovanemartins

MCP server for LocalStack AWS services, enabling AI agents to interact with local AWS infra.

30 installs/wk local only

Instacart

by markswendsen-code

MCP server for Instacart - let AI agents manage grocery shopping and place orders autonomously

80 installs/wk local only

Doordash

by markswendsen-code

MCP server for DoorDash - let AI agents order food delivery autonomously with browser-based ordering

67 installs/wk local only

MCP Victoriatraces

by victoriametrics-community

MCP Server for VictoriaTraces. Provides integration with VictoriaTraces API and documentation

local only

Browser Agent

by runbook-ai

MCP server for browser automation with AI agent

33 installs/wk local only

Inflow — questions

Answers built from our own checks of this server.

Why is there no tool list for Inflow?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.

Is Inflow working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 435 ms. The bar chart above shows every period we have measured.

How do I connect Inflow?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own key or an OAuth login: it refuses anonymous clients.

Does Inflow need an API key?

Yes. Every time we knock, Inflow answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is Inflow?

It answers our handshake in 435 ms on average, which is faster than 31% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Inflow open source?

Yes — it is published under the MIT licence and 6 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.